TOP ACTIVATIONS
MAX = 0.106

and Squirrel decided to share the pear and eat it together
of candy he had never seen before . He was so
happier . Soon , Spark y 's friends
inside and saw all kinds of candy he had never seen
" Give me some mint s , Lily !"
It was shiny and had lots of colors . She put
˜ Can I offer some p ears to my friends
. " Can I have some candy , Billy ?" Tim
mighty elephant named Ell a . Ell a was very big
It was shiny and had lots of colors . She put
and knocked over her jar of mar bles . They all
Y awn wanted to eat the pear , but he knew
As they ate the pear , they learned that
mom if she could have some , and her mom said
big elephant named Ell a . Ell a was very strong
tree ! Jane saw lots of p ears hanging , so
candy jar and ate too much candy . His tum my
umpy elephant named Ell y . Ell y had a long
. Now we can buy lots of treats !"
Yes , you can have some candy ." The nice little

MIN ACTIVATIONS
MIN = -0.108

there was a sheet . This sheet could talk . All
Just then , a chip m unk named Sam came by
which he loved to drive !
drum and Mia has a fl ute . They make different
the fire . The marsh m allows became all warm and
there was a sheep . This sheep was very sad .
was an enormous drum . This drum lived in a big
. They used a flashlight as the spotlight . They invited
mother 's : Peter , come
smiled and said It â
a very special human . This human filled the world with
mother holding a freshly - b aked muff in .
. It was a chip m unk ! The chip m
a big red bucket . This bucket loved to gain things
the screen , That looks really
was a rare seed . This seed could grow into a
Then , a small chip m unk scrambled down from the
scared . Suddenly , Juliet heard a voice .
When it started getting dark , Mild and her brother returned
forgot all about the marsh m allows . <|endoftext|> Once upon

INTERVAL 0.052 - 0.106
CONTAINS 0.174%

the park . She felt much better now that she had
sw am together every day . <|endoftext|> Once upon a time
and the kids never saw him again . <|endoftext|> Once upon
big hug . Tim my felt much better .
better . He looked at Lily and said , " Thank

INTERVAL -0.001 - 0.052
CONTAINS 52.136%

in his bedroom before bed time . He held the rock
said . The angel waved her hands and the
on him . From that day on , Red
'm studying !" The little boy was so amazed . He
to her and played baseball safely . <|endoftext|> Steve was a

INTERVAL -0.054 - -0.001
CONTAINS 47.609%

" Hello , kids !" the clown said . "
wide and he smiled . He saw lots of exciting things
Then they watched the sun set over the dark hill
kids first ". Jack nodded , disappointed .
beard and a robe . He looks angry .

INTERVAL -0.108 - -0.054
CONTAINS 0.081%

help her make the cob we bs . They loved playing
beautiful bracelet on the ground . It was so shiny and
smiled and said yes , â
a special home a hut .
to her !" Mia says . She hugs Anna and checks
Token and
Token ID290
Feature activation+1.94e-02

Pos logit contributions
 cand+0.012
rell+0.011
 sweets+0.010
 candy+0.010
 bamboo+0.010
Neg logit contributions
 Juliet-0.012
 Doug-0.011
 Donna-0.011
icker-0.011
avi-0.011
Token Squirrel
Token ID44259
Feature activation+3.07e-02

Pos logit contributions
 cand+0.035
rell+0.031
 sweets+0.030
reating+0.029
 carn+0.028
Neg logit contributions
 Donna-0.032
 Doug-0.032
 Juliet-0.032
 human-0.030
 Karl-0.029
Token decided
Token ID3066
Feature activation+1.27e-02

Pos logit contributions
 cand+0.054
 sweets+0.046
rell+0.045
reating+0.044
 candy+0.043
Neg logit contributions
 Juliet-0.050
 Doug-0.050
 Donna-0.049
 human-0.048
avi-0.047
Token to
Token ID284
Feature activation+2.15e-02

Pos logit contributions
 cand+0.029
rell+0.027
 sweets+0.025
 bamboo+0.025
 carn+0.024
Neg logit contributions
 Juliet-0.015
 Doug-0.014
 Donna-0.014
icker-0.013
 broom-0.013
Token share
Token ID2648
Feature activation+3.35e-02

Pos logit contributions
 cand+0.033
rell+0.028
 sweets+0.027
 bamboo+0.025
 carn+0.025
Neg logit contributions
 Juliet-0.040
 Doug-0.039
icker-0.039
 Donna-0.039
Jud-0.038
Token the
Token ID262
Feature activation+1.06e-01

Pos logit contributions
rell+0.070
 cand+0.066
 carn+0.061
reating+0.059
ogging+0.058
Neg logit contributions
 Juliet-0.039
 Doug-0.039
 human-0.039
kins-0.038
 Judy-0.038
Token pear
Token ID25286
Feature activation+3.75e-02

Pos logit contributions
reating+0.170
orting+0.161
rob+0.150
ogging+0.149
rell+0.148
Neg logit contributions
 ruler-0.149
 tool-0.145
 nail-0.145
 plant-0.145
 seed-0.144
Token and
Token ID290
Feature activation+3.23e-02

Pos logit contributions
 cand+0.057
rell+0.054
 carn+0.049
 sweets+0.048
reating+0.047
Neg logit contributions
kins-0.062
icker-0.062
 broom-0.061
ox-0.059
cker-0.058
Token eat
Token ID4483
Feature activation+3.45e-02

Pos logit contributions
 cand+0.051
rell+0.047
 carn+0.040
 sweets+0.040
hell+0.040
Neg logit contributions
 Doug-0.055
 Juliet-0.055
 Donna-0.054
 Judy-0.053
 human-0.053
Token it
Token ID340
Feature activation+1.37e-02

Pos logit contributions
rell+0.068
 cand+0.067
 carn+0.060
reating+0.058
 sweets+0.056
Neg logit contributions
kins-0.042
icker-0.042
 Doug-0.041
 Juliet-0.041
 broom-0.040
Token together
Token ID1978
Feature activation+1.03e-02

Pos logit contributions
 cand+0.024
rell+0.021
 sweets+0.020
 carn+0.019
reating+0.019
Neg logit contributions
 Juliet-0.023
icker-0.022
 Doug-0.022
 broom-0.021
 Donna-0.021
Token of
Token ID286
Feature activation+1.00e-01

Pos logit contributions
rell+0.101
 carn+0.090
 coaster+0.089
brate+0.088
 cand+0.088
Neg logit contributions
kins-0.091
icker-0.083
 broom-0.083
unk-0.082
 human-0.081
Token candy
Token ID18550
Feature activation+3.52e-02

Pos logit contributions
rell+0.159
ousel+0.144
round+0.140
orting+0.139
seek+0.138
Neg logit contributions
 pots-0.159
 pans-0.145
 curious-0.140
 human-0.136
 tools-0.136
Token he
Token ID339
Feature activation+5.46e-03

Pos logit contributions
 cand+0.060
rell+0.059
 bamboo+0.053
reating+0.053
 sweets+0.051
Neg logit contributions
kins-0.050
 broom-0.050
 stove-0.047
 Juliet-0.047
 Doug-0.047
Token had
Token ID550
Feature activation+3.33e-02

Pos logit contributions
 cand+0.011
rell+0.009
 sweets+0.009
 bamboo+0.009
 candy+0.009
Neg logit contributions
 Juliet-0.008
 Doug-0.008
icker-0.008
 Donna-0.008
ox-0.008
Token never
Token ID1239
Feature activation+4.34e-02

Pos logit contributions
 cand+0.062
rell+0.058
 bamboo+0.054
 sweets+0.053
reating+0.051
Neg logit contributions
 Juliet-0.045
ox-0.043
 broom-0.043
Jud-0.043
cker-0.042
Token seen
Token ID1775
Feature activation+1.04e-01

Pos logit contributions
 cand+0.098
rell+0.093
 bamboo+0.090
 sweets+0.084
 carn+0.083
Neg logit contributions
 Juliet-0.042
Jud-0.040
ox-0.040
cker-0.040
 broom-0.039
Token before
Token ID878
Feature activation+1.86e-02

Pos logit contributions
 cand+0.190
rell+0.190
 bamboo+0.167
From+0.158
 carn+0.158
Neg logit contributions
unk-0.118
 stove-0.117
 broom-0.114
icia-0.112
 human-0.111
Token.
Token ID13
Feature activation+1.95e-02

Pos logit contributions
 cand+0.037
rell+0.033
 sweets+0.032
 bamboo+0.031
reating+0.030
Neg logit contributions
 Juliet-0.025
 Doug-0.025
 broom-0.024
icker-0.024
 Donna-0.024
Token He
Token ID679
Feature activation+2.77e-02

Pos logit contributions
 cand+0.036
rell+0.031
reating+0.030
 sweets+0.030
 course+0.029
Neg logit contributions
 Doug-0.030
 Juliet-0.030
 Donna-0.029
icker-0.029
 broom-0.028
Token was
Token ID373
Feature activation+3.33e-02

Pos logit contributions
 cand+0.057
rell+0.056
reating+0.053
 sweets+0.051
 bamboo+0.050
Neg logit contributions
 Juliet-0.035
 Doug-0.035
Jud-0.034
 human-0.033
 Donna-0.033
Token so
Token ID523
Feature activation+1.41e-02

Pos logit contributions
 cand+0.061
rell+0.057
reating+0.053
 course+0.052
hell+0.051
Neg logit contributions
 Juliet-0.050
 human-0.049
 Doug-0.049
 Donna-0.048
 broom-0.048
Token happier
Token ID23030
Feature activation-1.29e-03

Pos logit contributions
 cand+0.091
rell+0.084
reating+0.083
 carn+0.079
round+0.076
Neg logit contributions
 broom-0.112
icker-0.104
 tool-0.100
 human-0.099
 pots-0.096
Token.
Token ID13
Feature activation+7.97e-02

Pos logit contributions
 Juliet+0.002
 Doug+0.002
icker+0.002
 Donna+0.002
ox+0.002
Neg logit contributions
 cand-0.002
rell-0.002
 sweets-0.002
 candy-0.002
 bamboo-0.002
Token
Token ID220
Feature activation+2.12e-02

Pos logit contributions
reating+0.160
 cand+0.158
 sweets+0.151
 desserts+0.139
 course+0.137
Neg logit contributions
 Juliet-0.089
 Doug-0.089
ometer-0.086
 Karl-0.083
 Shirley-0.081
Token
Token ID198
Feature activation+6.49e-02

Pos logit contributions
 cand+0.040
 sweets+0.033
rell+0.032
 candy+0.031
 bamboo+0.031
Neg logit contributions
icker-0.035
 Juliet-0.034
 Doug-0.034
 Donna-0.033
Jud-0.032
Token
Token ID198
Feature activation+7.44e-02

Pos logit contributions
 cand+0.168
 sweets+0.149
rell+0.137
 candy+0.136
reating+0.135
Neg logit contributions
 Juliet-0.062
Doug-0.062
 Doug-0.061
icker-0.056
Jud-0.056
TokenSoon
Token ID28093
Feature activation+1.04e-01

Pos logit contributions
 cand+0.138
 sweets+0.125
rell+0.116
 bamboo+0.114
 mango+0.108
Neg logit contributions
Doug-0.108
 human-0.102
 Juliet-0.101
icia-0.101
 Doug-0.100
Token,
Token ID11
Feature activation+7.36e-02

Pos logit contributions
reating+0.194
rell+0.189
round+0.187
ieved+0.186
uct+0.185
Neg logit contributions
 Doug-0.106
 human-0.102
 Juliet-0.098
 Karl-0.097
 Donna-0.097
Token Spark
Token ID17732
Feature activation-7.79e-03

Pos logit contributions
rell+0.114
 cand+0.108
 sweets+0.097
hell+0.096
reating+0.093
Neg logit contributions
 human-0.124
 Doug-0.123
 Juliet-0.119
 parent-0.114
 father-0.114
Tokeny
Token ID88
Feature activation+2.76e-03

Pos logit contributions
 Juliet+0.010
 Doug+0.010
icker+0.010
 Donna+0.010
 broom+0.009
Neg logit contributions
 cand-0.017
rell-0.015
 sweets-0.014
 candy-0.014
 bamboo-0.014
Token's
Token ID338
Feature activation-8.93e-03

Pos logit contributions
 cand+0.005
rell+0.004
 sweets+0.004
 candy+0.004
 bamboo+0.004
Neg logit contributions
 Juliet-0.005
 Doug-0.005
icker-0.005
 Donna-0.004
 broom-0.004
Token friends
Token ID2460
Feature activation+2.81e-02

Pos logit contributions
 Juliet+0.016
icker+0.016
 Doug+0.015
 Donna+0.015
Jud+0.015
Neg logit contributions
 cand-0.015
 sweets-0.013
rell-0.013
 candy-0.013
 bamboo-0.012
Token inside
Token ID2641
Feature activation+8.03e-04

Pos logit contributions
 cand+0.067
rell+0.059
 sweets+0.057
 course+0.055
 bamboo+0.055
Neg logit contributions
 Juliet-0.027
 broom-0.026
 Donna-0.024
icker-0.024
 Doug-0.024
Token and
Token ID290
Feature activation+2.46e-02

Pos logit contributions
 cand+0.001
rell+0.001
 sweets+0.001
 candy+0.001
 bamboo+0.001
Neg logit contributions
 Juliet-0.001
 Doug-0.001
icker-0.001
 Donna-0.001
 broom-0.001
Token saw
Token ID2497
Feature activation+3.66e-02

Pos logit contributions
 cand+0.055
rell+0.053
reating+0.049
 bamboo+0.048
hell+0.048
Neg logit contributions
 Juliet-0.029
 Doug-0.027
 Donna-0.026
 broom-0.026
 Karl-0.025
Token all
Token ID477
Feature activation+3.67e-02

Pos logit contributions
rell+0.072
 cand+0.068
ogging+0.061
hell+0.060
brate+0.058
Neg logit contributions
 Doug-0.049
 human-0.047
 stove-0.046
 Juliet-0.045
 Mother-0.045
Token kinds
Token ID6982
Feature activation+6.10e-02

Pos logit contributions
 cand+0.070
rell+0.061
 sweets+0.058
brate+0.057
 bamboo+0.056
Neg logit contributions
 Juliet-0.051
 human-0.049
 Doug-0.048
 Judy-0.048
 Donna-0.048
Token of
Token ID286
Feature activation+1.00e-01

Pos logit contributions
rell+0.101
 carn+0.090
 coaster+0.089
brate+0.088
 cand+0.088
Neg logit contributions
kins-0.091
icker-0.083
 broom-0.083
unk-0.082
 human-0.081
Token candy
Token ID18550
Feature activation+3.52e-02

Pos logit contributions
rell+0.159
ousel+0.144
round+0.140
orting+0.139
seek+0.138
Neg logit contributions
 pots-0.159
 pans-0.145
 curious-0.140
 human-0.136
 tools-0.136
Token he
Token ID339
Feature activation+5.46e-03

Pos logit contributions
 cand+0.060
rell+0.059
 bamboo+0.053
reating+0.053
 sweets+0.051
Neg logit contributions
kins-0.050
 broom-0.050
 stove-0.047
 Juliet-0.047
 Doug-0.047
Token had
Token ID550
Feature activation+3.33e-02

Pos logit contributions
 cand+0.011
rell+0.009
 sweets+0.009
 bamboo+0.009
 candy+0.009
Neg logit contributions
 Juliet-0.008
 Doug-0.008
icker-0.008
 Donna-0.008
ox-0.008
Token never
Token ID1239
Feature activation+4.34e-02

Pos logit contributions
 cand+0.062
rell+0.058
 bamboo+0.054
 sweets+0.053
reating+0.051
Neg logit contributions
 Juliet-0.045
ox-0.043
 broom-0.043
Jud-0.043
cker-0.042
Token seen
Token ID1775
Feature activation+1.04e-01

Pos logit contributions
 cand+0.098
rell+0.093
 bamboo+0.090
 sweets+0.084
 carn+0.083
Neg logit contributions
 Juliet-0.042
Jud-0.040
ox-0.040
cker-0.040
 broom-0.039
Token
Token ID198
Feature activation-2.29e-03

Pos logit contributions
 Juliet+0.013
icker+0.013
 Doug+0.013
 broom+0.013
avi+0.013
Neg logit contributions
 cand-0.010
rell-0.008
 sweets-0.008
 candy-0.008
 bamboo-0.008
Token
Token ID198
Feature activation-1.11e-04

Pos logit contributions
 Juliet+0.004
 Doug+0.004
icker+0.004
 Donna+0.004
 broom+0.004
Neg logit contributions
 cand-0.003
rell-0.003
 sweets-0.003
 candy-0.003
 bamboo-0.003
Token"
Token ID1
Feature activation-2.33e-02

Pos logit contributions
 Juliet+0.000
 Doug+0.000
icker+0.000
 Donna+0.000
ox+0.000
Neg logit contributions
 cand-0.000
rell-0.000
 sweets-0.000
 candy-0.000
 bamboo-0.000
TokenGive
Token ID23318
Feature activation+1.83e-02

Pos logit contributions
 Juliet+0.043
icker+0.042
 Doug+0.042
ox+0.041
 Karl+0.040
Neg logit contributions
 cand-0.041
 sweets-0.033
 candy-0.032
 bamboo-0.030
 course-0.030
Token me
Token ID502
Feature activation+1.04e-02

Pos logit contributions
 cand+0.029
rell+0.024
 sweets+0.024
 bamboo+0.023
 carn+0.022
Neg logit contributions
 Juliet-0.034
 Doug-0.033
 Donna-0.032
icia-0.031
 human-0.031
Token some
Token ID617
Feature activation+9.80e-02

Pos logit contributions
 cand+0.016
rell+0.013
 sweets+0.013
 carn+0.012
 candy+0.012
Neg logit contributions
 Juliet-0.020
 Doug-0.020
icker-0.019
 Donna-0.019
 broom-0.019
Token mint
Token ID21043
Feature activation+3.65e-02

Pos logit contributions
 coaster+0.154
 carn+0.149
ousel+0.149
seek+0.142
ulk+0.137
Neg logit contributions
 pots-0.131
 scissors-0.123
 tool-0.122
 knob-0.122
 hose-0.121
Tokens
Token ID82
Feature activation+4.52e-02

Pos logit contributions
 cand+0.054
 carn+0.049
rell+0.049
 sweets+0.047
reating+0.046
Neg logit contributions
kins-0.059
 broom-0.058
 Donna-0.058
icker-0.058
 Doug-0.057
Token,
Token ID11
Feature activation+1.08e-02

Pos logit contributions
 cand+0.074
 carn+0.068
rell+0.067
 sweets+0.063
reating+0.062
Neg logit contributions
 broom-0.070
icker-0.067
ox-0.066
 stove-0.066
unk-0.066
Token Lily
Token ID20037
Feature activation-2.09e-02

Pos logit contributions
 cand+0.020
rell+0.018
 sweets+0.017
 carn+0.016
 bamboo+0.016
Neg logit contributions
 Juliet-0.017
 Doug-0.016
 Donna-0.016
icker-0.016
 broom-0.016
Token!"
Token ID2474
Feature activation-1.42e-02

Pos logit contributions
 Juliet+0.049
icker+0.049
 Doug+0.047
 Donna+0.046
Jud+0.046
Neg logit contributions
 cand-0.024
rell-0.018
 sweets-0.018
 candy-0.017
 bamboo-0.016
Token It
Token ID632
Feature activation+3.13e-02

Pos logit contributions
 cand+0.024
rell+0.021
 sweets+0.021
reating+0.020
 bamboo+0.020
Neg logit contributions
 Juliet-0.017
 Doug-0.016
 Donna-0.016
icker-0.016
 broom-0.016
Token was
Token ID373
Feature activation+4.12e-02

Pos logit contributions
 cand+0.064
reating+0.059
 sweets+0.057
rell+0.056
ogging+0.054
Neg logit contributions
 Juliet-0.040
 Doug-0.039
 Donna-0.038
 broom-0.038
 human-0.037
Token shiny
Token ID22441
Feature activation+2.59e-02

Pos logit contributions
 cand+0.083
rell+0.080
ogging+0.072
 carn+0.072
 course+0.071
Neg logit contributions
 Juliet-0.051
 broom-0.051
 human-0.049
 Donna-0.049
 Doug-0.048
Token and
Token ID290
Feature activation+2.86e-02

Pos logit contributions
 cand+0.050
rell+0.047
 sweets+0.044
reating+0.044
 carn+0.043
Neg logit contributions
 broom-0.034
 human-0.033
 Juliet-0.033
 Doug-0.032
ox-0.032
Token had
Token ID550
Feature activation+4.12e-02

Pos logit contributions
 cand+0.059
rell+0.055
reating+0.052
 sweets+0.050
 carn+0.050
Neg logit contributions
 Juliet-0.037
 Doug-0.035
 Donna-0.035
 broom-0.033
 human-0.033
Token lots
Token ID6041
Feature activation+9.59e-02

Pos logit contributions
 cand+0.083
rell+0.077
ogging+0.073
 sweets+0.073
 carn+0.072
Neg logit contributions
 Juliet-0.052
 broom-0.049
ox-0.048
 human-0.048
 Doug-0.046
Token of
Token ID286
Feature activation+8.68e-02

Pos logit contributions
rob+0.171
|+0.168
 carn+0.168
ieved+0.164
brate+0.163
Neg logit contributions
 broom-0.111
 knob-0.099
 human-0.095
obs-0.095
 tool-0.095
Token colors
Token ID7577
Feature activation+3.24e-02

Pos logit contributions
 carn+0.203
orting+0.199
ogging+0.197
ousel+0.188
rell+0.187
Neg logit contributions
 scissors-0.062
 broom-0.061
 knob-0.059
 pots-0.052
 tool-0.050
Token.
Token ID13
Feature activation+2.45e-02

Pos logit contributions
 cand+0.063
 sweets+0.055
 carn+0.055
rell+0.055
 bamboo+0.052
Neg logit contributions
 Juliet-0.044
 broom-0.044
icker-0.042
 Doug-0.042
ox-0.041
Token She
Token ID1375
Feature activation+2.10e-02

Pos logit contributions
 cand+0.046
reating+0.040
rell+0.039
 sweets+0.039
 carn+0.039
Neg logit contributions
 Juliet-0.038
 Donna-0.037
 Doug-0.036
 Judy-0.035
icker-0.035
Token put
Token ID1234
Feature activation+2.55e-02

Pos logit contributions
 cand+0.044
rell+0.041
reating+0.039
 sweets+0.039
 bamboo+0.038
Neg logit contributions
 Juliet-0.027
 Doug-0.026
ox-0.026
 Donna-0.025
 human-0.025
Token
Token ID26391
Feature activation-5.40e-02

Pos logit contributions
 Juliet+0.014
icker+0.014
 Doug+0.014
 broom+0.013
 Donna+0.013
Neg logit contributions
 cand-0.016
rell-0.014
 sweets-0.014
 candy-0.013
 carn-0.013
Token˜
Token ID41185
Feature activation-2.09e-02

Pos logit contributions
cker+0.089
icker+0.088
 Doug+0.083
 broom+0.083
 Juliet+0.080
Neg logit contributions
 cand-0.093
rell-0.081
 sweets-0.079
 candy-0.078
 carn-0.076
TokenCan
Token ID6090
Feature activation+1.33e-02

Pos logit contributions
icker+0.042
 Juliet+0.042
 Doug+0.041
ox+0.041
Jud+0.041
Neg logit contributions
 cand-0.029
 sweets-0.024
rell-0.024
 candy-0.023
 bamboo-0.022
Token I
Token ID314
Feature activation+2.05e-02

Pos logit contributions
 cand+0.021
rell+0.018
 sweets+0.017
 bamboo+0.017
 candy+0.016
Neg logit contributions
 Juliet-0.024
icker-0.023
 Doug-0.023
 Donna-0.023
ox-0.023
Token offer
Token ID2897
Feature activation+3.18e-02

Pos logit contributions
 cand+0.037
rell+0.032
 sweets+0.031
 bamboo+0.029
reating+0.029
Neg logit contributions
 Juliet-0.033
icker-0.032
 Doug-0.031
 Donna-0.031
 broom-0.031
Token some
Token ID617
Feature activation+9.57e-02

Pos logit contributions
 cand+0.051
rell+0.048
 carn+0.042
 sweets+0.041
 bamboo+0.041
Neg logit contributions
 Juliet-0.056
 Doug-0.053
 Donna-0.052
 Judy-0.051
 human-0.049
Token p
Token ID279
Feature activation+4.95e-02

Pos logit contributions
rell+0.139
 coaster+0.137
 cand+0.130
 carn+0.125
ousel+0.125
Neg logit contributions
 pots-0.133
 broom-0.133
 ruler-0.126
 tool-0.126
 knob-0.125
Tokenears
Token ID4127
Feature activation+3.27e-02

Pos logit contributions
 cand+0.084
rell+0.073
 carn+0.072
 sweets+0.072
 course+0.071
Neg logit contributions
icker-0.074
unk-0.068
ox-0.068
ierce-0.067
 broom-0.066
Token to
Token ID284
Feature activation+4.89e-02

Pos logit contributions
 cand+0.054
rell+0.048
 sweets+0.044
 carn+0.043
 bamboo+0.042
Neg logit contributions
 Juliet-0.053
icker-0.052
 broom-0.051
 Donna-0.051
kins-0.050
Token my
Token ID616
Feature activation+3.59e-02

Pos logit contributions
 cand+0.087
rell+0.082
hell+0.072
 carn+0.071
 coaster+0.071
Neg logit contributions
 Juliet-0.069
 Donna-0.068
icker-0.068
 Doug-0.068
 Judy-0.067
Token friends
Token ID2460
Feature activation+2.05e-02

Pos logit contributions
 cand+0.068
rell+0.068
reating+0.062
hell+0.058
 sweets+0.058
Neg logit contributions
 broom-0.047
 human-0.047
 Juliet-0.046
ox-0.044
 stove-0.043
Token.
Token ID13
Feature activation-1.35e-02

Pos logit contributions
 cand+0.005
rell+0.004
 sweets+0.004
 candy+0.004
 bamboo+0.004
Neg logit contributions
 Juliet-0.004
 Doug-0.004
icker-0.004
 Donna-0.004
 broom-0.004
Token "
Token ID366
Feature activation+2.85e-03

Pos logit contributions
 Juliet+0.028
icker+0.028
avi+0.027
ox+0.027
Jud+0.027
Neg logit contributions
 cand-0.019
rell-0.016
 sweets-0.015
 candy-0.015
 carn-0.014
TokenCan
Token ID6090
Feature activation+1.46e-02

Pos logit contributions
 cand+0.005
rell+0.004
 sweets+0.004
 candy+0.004
 bamboo+0.004
Neg logit contributions
 Juliet-0.005
 Doug-0.005
icker-0.005
 Donna-0.005
Jud-0.005
Token I
Token ID314
Feature activation+3.07e-02

Pos logit contributions
 cand+0.026
rell+0.023
 sweets+0.022
 bamboo+0.021
reating+0.021
Neg logit contributions
 Doug-0.024
 Juliet-0.023
 Donna-0.023
icker-0.022
ox-0.022
Token have
Token ID423
Feature activation+7.31e-02

Pos logit contributions
 cand+0.054
rell+0.047
reating+0.045
 sweets+0.044
 bamboo+0.043
Neg logit contributions
icker-0.046
 Donna-0.046
 broom-0.046
 Juliet-0.045
 Doug-0.045
Token some
Token ID617
Feature activation+9.54e-02

Pos logit contributions
rell+0.142
ogging+0.135
 cand+0.130
whe+0.128
reating+0.128
Neg logit contributions
 tool-0.072
 pots-0.071
 dad-0.067
 tractor-0.067
 Doug-0.066
Token candy
Token ID18550
Feature activation+4.97e-02

Pos logit contributions
|+0.130
 coaster+0.120
rell+0.116
 carn+0.115
seek+0.113
Neg logit contributions
 tool-0.150
 pots-0.141
 dad-0.140
 scissors-0.139
 knife-0.139
Token,
Token ID11
Feature activation+6.01e-03

Pos logit contributions
rell+0.081
 cand+0.080
 bamboo+0.073
 carn+0.070
 sweets+0.069
Neg logit contributions
icker-0.070
kins-0.070
 tool-0.069
 broom-0.068
 stove-0.067
Token Billy
Token ID15890
Feature activation+2.33e-03

Pos logit contributions
 cand+0.011
rell+0.010
 sweets+0.009
 bamboo+0.009
 candy+0.009
Neg logit contributions
 Juliet-0.010
 Doug-0.009
 Donna-0.009
icker-0.009
 broom-0.009
Token?"
Token ID1701
Feature activation-1.16e-02

Pos logit contributions
 cand+0.004
rell+0.004
 sweets+0.004
 candy+0.003
 bamboo+0.003
Neg logit contributions
 Juliet-0.004
 Doug-0.004
icker-0.004
 Donna-0.004
ox-0.004
Token Tim
Token ID5045
Feature activation+1.72e-02

Pos logit contributions
icker+0.024
 Juliet+0.024
ox+0.023
avi+0.023
 broom+0.023
Neg logit contributions
 cand-0.016
rell-0.013
 sweets-0.013
 candy-0.013
 bamboo-0.012
Token mighty
Token ID18680
Feature activation+2.03e-02

Pos logit contributions
 Juliet+0.005
 Doug+0.004
icker+0.004
 Donna+0.004
ox+0.004
Neg logit contributions
 cand-0.006
rell-0.005
 sweets-0.005
 candy-0.005
 bamboo-0.005
Token elephant
Token ID20950
Feature activation+2.68e-03

Pos logit contributions
 cand+0.040
rell+0.035
 sweets+0.034
reating+0.033
 candy+0.032
Neg logit contributions
 Juliet-0.029
 human-0.029
 Doug-0.029
 broom-0.028
 tractor-0.028
Token named
Token ID3706
Feature activation-1.86e-04

Pos logit contributions
 cand+0.005
rell+0.004
 sweets+0.004
 candy+0.004
 bamboo+0.004
Neg logit contributions
 Juliet-0.005
 Doug-0.004
icker-0.004
 Donna-0.004
ox-0.004
Token Ell
Token ID7122
Feature activation-3.29e-02

Pos logit contributions
 Juliet+0.000
 Doug+0.000
icker+0.000
 Donna+0.000
ox+0.000
Neg logit contributions
 cand-0.000
rell-0.000
 sweets-0.000
 candy-0.000
 bamboo-0.000
Tokena
Token ID64
Feature activation-1.43e-02

Pos logit contributions
 Doug+0.035
 Juliet+0.032
 Donna+0.032
 broom+0.029
 Judy+0.028
Neg logit contributions
 cand-0.081
reating-0.070
rell-0.070
 bamboo-0.069
hell-0.068
Token.
Token ID13
Feature activation+9.54e-02

Pos logit contributions
 Juliet+0.026
 Doug+0.026
icker+0.025
 Donna+0.025
 broom+0.024
Neg logit contributions
 cand-0.023
rell-0.019
 sweets-0.019
 bamboo-0.019
 candy-0.019
Token Ell
Token ID7122
Feature activation-2.13e-02

Pos logit contributions
 course+0.171
 cand+0.170
ieved+0.162
orting+0.162
reating+0.160
Neg logit contributions
 Mir-0.100
 Jess-0.096
 maj-0.093
 dunno-0.091
 Karl-0.091
Tokena
Token ID64
Feature activation+1.30e-02

Pos logit contributions
 Doug+0.018
 Juliet+0.018
 Donna+0.017
 broom+0.016
 Judy+0.015
Neg logit contributions
 cand-0.056
rell-0.049
 sweets-0.048
 bamboo-0.048
 candy-0.048
Token was
Token ID373
Feature activation-4.38e-03

Pos logit contributions
 cand+0.023
rell+0.020
 sweets+0.020
reating+0.019
 candy+0.019
Neg logit contributions
 Juliet-0.021
 Doug-0.021
icker-0.020
ox-0.020
avi-0.020
Token very
Token ID845
Feature activation-2.70e-02

Pos logit contributions
 Juliet+0.008
icker+0.008
 Doug+0.008
ox+0.008
 Donna+0.008
Neg logit contributions
 cand-0.007
rell-0.006
 sweets-0.006
 candy-0.006
 bamboo-0.006
Token big
Token ID1263
Feature activation-8.12e-03

Pos logit contributions
 Juliet+0.044
ox+0.043
 Doug+0.043
 broom+0.043
 tractor+0.042
Neg logit contributions
 cand-0.047
 candy-0.041
rell-0.041
 sweets-0.040
 bamboo-0.040
Token It
Token ID632
Feature activation+3.00e-02

Pos logit contributions
 cand+0.028
rell+0.024
 sweets+0.024
reating+0.023
 bamboo+0.023
Neg logit contributions
 Juliet-0.020
 Donna-0.019
 Doug-0.019
icker-0.019
 broom-0.018
Token was
Token ID373
Feature activation+3.77e-02

Pos logit contributions
 cand+0.061
reating+0.056
 sweets+0.054
rell+0.053
 carn+0.050
Neg logit contributions
 Juliet-0.039
 Doug-0.038
 Donna-0.038
 broom-0.037
 human-0.036
Token shiny
Token ID22441
Feature activation+2.45e-02

Pos logit contributions
 cand+0.074
rell+0.070
 carn+0.063
 sweets+0.063
ogging+0.063
Neg logit contributions
 Juliet-0.050
 broom-0.049
 Donna-0.048
 human-0.048
 Doug-0.047
Token and
Token ID290
Feature activation+2.66e-02

Pos logit contributions
 cand+0.047
rell+0.044
 sweets+0.041
reating+0.041
 carn+0.041
Neg logit contributions
 broom-0.033
 human-0.032
 Juliet-0.032
 Doug-0.031
 Donna-0.031
Token had
Token ID550
Feature activation+4.12e-02

Pos logit contributions
 cand+0.055
rell+0.051
reating+0.048
 sweets+0.047
 carn+0.046
Neg logit contributions
 Juliet-0.035
 Doug-0.033
 Donna-0.033
 broom-0.031
 human-0.031
Token lots
Token ID6041
Feature activation+9.51e-02

Pos logit contributions
 cand+0.083
rell+0.077
 sweets+0.072
ogging+0.072
 carn+0.072
Neg logit contributions
 Juliet-0.053
 broom-0.050
ox-0.049
 human-0.048
 Doug-0.046
Token of
Token ID286
Feature activation+8.82e-02

Pos logit contributions
rob+0.165
|+0.164
 carn+0.164
brate+0.158
ieved+0.157
Neg logit contributions
 broom-0.112
 knob-0.101
 human-0.096
obs-0.096
 tool-0.095
Token colors
Token ID7577
Feature activation+3.27e-02

Pos logit contributions
 carn+0.206
orting+0.199
ogging+0.199
ousel+0.191
reating+0.188
Neg logit contributions
 broom-0.060
 scissors-0.060
 knob-0.059
 pots-0.052
ox-0.051
Token.
Token ID13
Feature activation+2.94e-02

Pos logit contributions
 cand+0.062
rell+0.054
 sweets+0.054
 carn+0.053
 bamboo+0.051
Neg logit contributions
 Juliet-0.046
 broom-0.046
icker-0.044
 Doug-0.043
ox-0.043
Token She
Token ID1375
Feature activation+2.14e-02

Pos logit contributions
 cand+0.055
reating+0.049
rell+0.048
 carn+0.047
 sweets+0.047
Neg logit contributions
 Juliet-0.045
 Donna-0.043
 Judy-0.042
 Doug-0.041
icker-0.041
Token put
Token ID1234
Feature activation+2.81e-02

Pos logit contributions
 cand+0.044
rell+0.041
reating+0.039
 sweets+0.039
 bamboo+0.038
Neg logit contributions
 Juliet-0.028
 Doug-0.027
ox-0.027
 Donna-0.026
 human-0.026
Token and
Token ID290
Feature activation-5.48e-03

Pos logit contributions
 Doug+0.074
 Juliet+0.073
avi+0.071
 Donna+0.071
Doug+0.070
Neg logit contributions
 cand-0.048
 candy-0.037
 sweets-0.037
 again-0.037
rell-0.036
Token knocked
Token ID13642
Feature activation+1.94e-02

Pos logit contributions
 Juliet+0.009
icker+0.009
 Doug+0.008
avi+0.008
 Donna+0.008
Neg logit contributions
 cand-0.010
 sweets-0.009
rell-0.009
 candy-0.009
 bamboo-0.008
Token over
Token ID625
Feature activation-2.49e-03

Pos logit contributions
 cand+0.035
rell+0.029
 carn+0.029
 sweets+0.028
 bamboo+0.027
Neg logit contributions
 Juliet-0.032
 Doug-0.032
 broom-0.031
 Donna-0.031
icker-0.031
Token her
Token ID607
Feature activation+4.75e-02

Pos logit contributions
 Juliet+0.004
 Doug+0.004
icker+0.004
 Donna+0.004
avi+0.004
Neg logit contributions
 cand-0.004
rell-0.004
 sweets-0.004
 candy-0.004
 bamboo-0.003
Token jar
Token ID17379
Feature activation-9.91e-03

Pos logit contributions
 cand+0.066
reating+0.066
rell+0.066
 course+0.064
brate+0.063
Neg logit contributions
 human-0.082
 tool-0.081
 broom-0.080
unk-0.078
kins-0.076
Token of
Token ID286
Feature activation+9.48e-02

Pos logit contributions
 Juliet+0.018
 Doug+0.017
avi+0.017
icker+0.017
 Donna+0.017
Neg logit contributions
 cand-0.017
rell-0.014
 sweets-0.014
 candy-0.014
 bamboo-0.013
Token mar
Token ID1667
Feature activation+1.17e-02

Pos logit contributions
seek+0.152
rell+0.152
adays+0.151
ival+0.149
ieved+0.148
Neg logit contributions
 pots-0.145
 pans-0.137
 scissors-0.125
 tool-0.121
 sp-0.121
Tokenbles
Token ID7689
Feature activation+1.02e-02

Pos logit contributions
 cand+0.027
rell+0.024
 sweets+0.024
 bamboo+0.023
 candy+0.023
Neg logit contributions
icker-0.013
 Juliet-0.013
 Doug-0.012
ox-0.012
 broom-0.012
Token.
Token ID13
Feature activation+1.19e-02

Pos logit contributions
 cand+0.020
rell+0.017
 sweets+0.017
 bamboo+0.016
 candy+0.016
Neg logit contributions
 Juliet-0.015
 broom-0.015
icker-0.015
 Doug-0.015
 Donna-0.014
Token They
Token ID1119
Feature activation+8.28e-03

Pos logit contributions
 cand+0.022
rell+0.018
 sweets+0.018
reating+0.018
 bamboo+0.017
Neg logit contributions
 Juliet-0.019
 Doug-0.019
icker-0.018
 broom-0.018
 Donna-0.018
Token all
Token ID477
Feature activation+1.22e-02

Pos logit contributions
 cand+0.014
rell+0.012
 sweets+0.011
 carn+0.011
 bamboo+0.011
Neg logit contributions
 Juliet-0.015
 Doug-0.015
icker-0.014
 broom-0.014
 Donna-0.014
TokenY
Token ID56
Feature activation+3.34e-02

Pos logit contributions
 cand+0.079
rell+0.071
 sweets+0.068
reating+0.063
 candy+0.063
Neg logit contributions
zzy-0.047
Jud-0.046
 Juliet-0.045
 human-0.045
 Donna-0.044
Tokenawn
Token ID3832
Feature activation-7.14e-03

Pos logit contributions
 cand+0.061
 sweets+0.054
 carn+0.052
 bamboo+0.052
 candy+0.050
Neg logit contributions
icker-0.055
 Juliet-0.050
Jud-0.049
 Doug-0.048
ox-0.048
Token wanted
Token ID2227
Feature activation+2.33e-02

Pos logit contributions
 Juliet+0.012
icker+0.012
 Doug+0.011
 Donna+0.011
 broom+0.011
Neg logit contributions
 cand-0.013
 sweets-0.011
rell-0.011
 candy-0.010
 bamboo-0.010
Token to
Token ID284
Feature activation+3.84e-02

Pos logit contributions
 cand+0.057
rell+0.056
reating+0.050
 carn+0.050
 sweets+0.049
Neg logit contributions
 Doug-0.021
 Juliet-0.021
 broom-0.019
 Donna-0.019
 human-0.019
Token eat
Token ID4483
Feature activation+7.28e-02

Pos logit contributions
 cand+0.077
rell+0.070
reating+0.064
 carn+0.063
 sweets+0.062
Neg logit contributions
 Juliet-0.051
 broom-0.051
 Doug-0.051
 Judy-0.050
 Donna-0.050
Token the
Token ID262
Feature activation+9.40e-02

Pos logit contributions
rell+0.159
 cand+0.145
 carn+0.144
reating+0.143
chair+0.141
Neg logit contributions
 pots-0.069
 Miles-0.061
 stove-0.061
 plant-0.059
 Judy-0.059
Token pear
Token ID25286
Feature activation+2.14e-02

Pos logit contributions
reating+0.148
orting+0.147
rob+0.131
ogging+0.130
ousel+0.129
Neg logit contributions
 knob-0.140
 ruler-0.139
 seed-0.133
 plant-0.133
 pots-0.131
Token,
Token ID11
Feature activation+9.20e-03

Pos logit contributions
 cand+0.031
rell+0.027
 carn+0.025
 sweets+0.025
reating+0.025
Neg logit contributions
 broom-0.039
 Juliet-0.038
 Doug-0.038
icker-0.038
 Donna-0.038
Token but
Token ID475
Feature activation+1.23e-02

Pos logit contributions
 cand+0.015
rell+0.013
 sweets+0.012
 candy+0.011
 bamboo+0.011
Neg logit contributions
 Juliet-0.017
 Doug-0.017
 Donna-0.016
 broom-0.016
icker-0.016
Token he
Token ID339
Feature activation-2.84e-03

Pos logit contributions
 cand+0.020
rell+0.017
 sweets+0.016
reating+0.015
 bamboo+0.015
Neg logit contributions
 Juliet-0.023
 Doug-0.023
 Donna-0.022
 human-0.022
icker-0.022
Token knew
Token ID2993
Feature activation+1.11e-02

Pos logit contributions
 Juliet+0.005
icker+0.005
 Doug+0.005
 Donna+0.005
 broom+0.005
Neg logit contributions
 cand-0.005
rell-0.004
 sweets-0.004
 candy-0.004
 bamboo-0.004
Token
Token ID198
Feature activation+2.77e-02

Pos logit contributions
 cand+0.039
 sweets+0.034
reating+0.033
rell+0.032
 candy+0.032
Neg logit contributions
 Juliet-0.032
 Doug-0.032
 Donna-0.032
icker-0.030
 Karl-0.030
Token
Token ID198
Feature activation+2.60e-02

Pos logit contributions
 cand+0.055
 sweets+0.047
rell+0.046
 candy+0.044
reating+0.043
Neg logit contributions
icker-0.042
 Juliet-0.042
 Doug-0.042
Jud-0.040
 Donna-0.040
TokenAs
Token ID1722
Feature activation+2.11e-02

Pos logit contributions
 cand+0.048
rell+0.042
 sweets+0.041
 candy+0.039
reating+0.037
Neg logit contributions
icker-0.040
Jud-0.040
 Juliet-0.040
 Doug-0.040
 Donna-0.040
Token they
Token ID484
Feature activation+7.53e-02

Pos logit contributions
 cand+0.049
rell+0.044
 sweets+0.043
reating+0.042
hell+0.040
Neg logit contributions
 Donna-0.025
 Juliet-0.025
 Doug-0.025
 human-0.024
icker-0.023
Token ate
Token ID15063
Feature activation+5.46e-02

Pos logit contributions
reating+0.142
rell+0.133
 cand+0.126
ogging+0.120
shadow+0.118
Neg logit contributions
 watered-0.104
icker-0.088
kins-0.088
aped-0.086
Jud-0.084
Token the
Token ID262
Feature activation+9.34e-02

Pos logit contributions
 cand+0.105
rell+0.105
reating+0.105
 carn+0.101
 coaster+0.095
Neg logit contributions
icker-0.064
 hose-0.063
 pots-0.063
 broom-0.062
 Donna-0.062
Token pear
Token ID25286
Feature activation+3.15e-02

Pos logit contributions
reating+0.161
orting+0.148
rob+0.141
ousel+0.139
brate+0.135
Neg logit contributions
 ruler-0.126
 plant-0.123
 bucket-0.122
 pots-0.122
 seed-0.119
Token,
Token ID11
Feature activation-6.02e-03

Pos logit contributions
 cand+0.043
reating+0.038
 carn+0.037
rell+0.037
 sweets+0.035
Neg logit contributions
 broom-0.059
icker-0.058
 Doug-0.057
kins-0.057
 Donna-0.056
Token they
Token ID484
Feature activation+1.40e-02

Pos logit contributions
 Juliet+0.011
icker+0.011
 Doug+0.011
ox+0.011
avi+0.011
Neg logit contributions
 cand-0.010
rell-0.008
 sweets-0.008
 candy-0.008
 bamboo-0.008
Token learned
Token ID4499
Feature activation+6.40e-03

Pos logit contributions
 cand+0.025
rell+0.023
 sweets+0.021
 bamboo+0.021
 candy+0.020
Neg logit contributions
 Juliet-0.023
 Doug-0.022
icker-0.022
 Donna-0.022
Jud-0.021
Token that
Token ID326
Feature activation+1.81e-02

Pos logit contributions
 cand+0.010
rell+0.009
 sweets+0.008
 candy+0.008
 bamboo+0.008
Neg logit contributions
 Juliet-0.012
 Doug-0.011
icker-0.011
 Donna-0.011
ox-0.011
Token mom
Token ID1995
Feature activation+2.26e-02

Pos logit contributions
 cand+0.008
rell+0.007
 sweets+0.007
 candy+0.007
 bamboo+0.007
Neg logit contributions
 Juliet-0.003
 Doug-0.003
icker-0.003
 Donna-0.003
 broom-0.003
Token if
Token ID611
Feature activation-2.73e-02

Pos logit contributions
 cand+0.040
rell+0.036
 carn+0.033
 sweets+0.033
 bamboo+0.032
Neg logit contributions
 Juliet-0.037
 Doug-0.036
 Donna-0.036
icker-0.035
 Judy-0.035
Token she
Token ID673
Feature activation-1.49e-02

Pos logit contributions
icker+0.056
ox+0.054
avi+0.053
 Juliet+0.053
 Doug+0.053
Neg logit contributions
 cand-0.042
 sweets-0.034
 candy-0.034
 bamboo-0.029
 course-0.028
Token could
Token ID714
Feature activation+1.50e-02

Pos logit contributions
 Juliet+0.024
icker+0.024
 Doug+0.022
 broom+0.022
 Donna+0.022
Neg logit contributions
 cand-0.028
 sweets-0.024
 candy-0.024
rell-0.023
 bamboo-0.022
Token have
Token ID423
Feature activation+7.51e-02

Pos logit contributions
 cand+0.025
rell+0.021
 sweets+0.020
 bamboo+0.019
reating+0.019
Neg logit contributions
 Juliet-0.026
icker-0.026
 Doug-0.026
 Donna-0.026
 broom-0.026
Token some
Token ID617
Feature activation+9.28e-02

Pos logit contributions
rell+0.144
ogging+0.142
reating+0.137
orting+0.134
 bamboo+0.134
Neg logit contributions
 tool-0.070
 Donna-0.068
 pots-0.067
 Judy-0.067
 Juliet-0.065
Token,
Token ID11
Feature activation-7.52e-04

Pos logit contributions
reating+0.117
 coaster+0.117
rell+0.115
ousel+0.115
From+0.112
Neg logit contributions
 pots-0.141
 tool-0.138
 scissors-0.133
 tools-0.131
 knife-0.128
Token and
Token ID290
Feature activation-1.58e-02

Pos logit contributions
 Juliet+0.001
 Doug+0.001
icker+0.001
 Donna+0.001
ox+0.001
Neg logit contributions
 cand-0.001
rell-0.001
 sweets-0.001
 candy-0.001
 bamboo-0.001
Token her
Token ID607
Feature activation-1.42e-02

Pos logit contributions
icker+0.030
 Juliet+0.029
avi+0.029
ox+0.029
 Doug+0.028
Neg logit contributions
 cand-0.026
 sweets-0.022
 candy-0.021
rell-0.020
 bamboo-0.019
Token mom
Token ID1995
Feature activation-6.43e-04

Pos logit contributions
 Juliet+0.019
icker+0.019
 Doug+0.019
avi+0.019
Jud+0.018
Neg logit contributions
 cand-0.031
 sweets-0.027
 candy-0.027
rell-0.026
 bamboo-0.025
Token said
Token ID531
Feature activation+6.53e-03

Pos logit contributions
 Juliet+0.001
 Doug+0.001
icker+0.001
 Donna+0.001
ox+0.001
Neg logit contributions
 cand-0.001
rell-0.001
 sweets-0.001
 candy-0.001
 bamboo-0.001
Token big
Token ID1263
Feature activation+2.02e-02

Pos logit contributions
 Juliet+0.035
 Doug+0.035
icker+0.033
 Donna+0.033
ox+0.033
Neg logit contributions
 cand-0.036
 candy-0.031
 sweets-0.030
 bamboo-0.030
 carn-0.029
Token elephant
Token ID20950
Feature activation+1.46e-02

Pos logit contributions
 cand+0.039
rell+0.035
 sweets+0.033
reating+0.031
 candy+0.031
Neg logit contributions
 Juliet-0.031
 human-0.030
 Doug-0.029
icker-0.029
 Donna-0.029
Token named
Token ID3706
Feature activation+8.35e-03

Pos logit contributions
 cand+0.028
rell+0.024
 sweets+0.024
 candy+0.023
reating+0.022
Neg logit contributions
 Juliet-0.022
icker-0.022
 Doug-0.022
 human-0.022
ox-0.022
Token Ell
Token ID7122
Feature activation-2.09e-02

Pos logit contributions
 cand+0.014
rell+0.012
 sweets+0.012
 candy+0.011
 bamboo+0.011
Neg logit contributions
 Juliet-0.015
 Doug-0.014
 Donna-0.014
icker-0.014
Jud-0.014
Tokena
Token ID64
Feature activation-4.99e-03

Pos logit contributions
 Doug+0.018
 Juliet+0.017
 Donna+0.016
 broom+0.015
 Judy+0.015
Neg logit contributions
 cand-0.056
rell-0.049
 sweets-0.048
reating-0.048
 bamboo-0.048
Token.
Token ID13
Feature activation+9.28e-02

Pos logit contributions
 Juliet+0.008
 Doug+0.008
icker+0.008
 Donna+0.008
 broom+0.008
Neg logit contributions
 cand-0.009
rell-0.007
 sweets-0.007
 candy-0.007
 bamboo-0.007
Token Ell
Token ID7122
Feature activation-1.37e-02

Pos logit contributions
 cand+0.166
 course+0.163
ieved+0.158
reating+0.155
orting+0.155
Neg logit contributions
 Mir-0.102
 Jess-0.101
 Juliet-0.095
 Ali-0.095
 pots-0.094
Tokena
Token ID64
Feature activation+2.42e-02

Pos logit contributions
 Juliet+0.009
 Doug+0.009
 Donna+0.009
 broom+0.008
icker+0.008
Neg logit contributions
 cand-0.038
rell-0.034
 sweets-0.034
 bamboo-0.033
 candy-0.033
Token was
Token ID373
Feature activation+1.96e-03

Pos logit contributions
 cand+0.045
rell+0.040
 sweets+0.039
reating+0.039
 candy+0.037
Neg logit contributions
 Juliet-0.037
 Doug-0.036
avi-0.036
 human-0.036
ox-0.036
Token very
Token ID845
Feature activation-2.02e-02

Pos logit contributions
 cand+0.003
rell+0.003
 sweets+0.003
 candy+0.003
 bamboo+0.003
Neg logit contributions
 Juliet-0.003
 Doug-0.003
icker-0.003
 Donna-0.003
 broom-0.003
Token strong
Token ID1913
Feature activation-1.35e-02

Pos logit contributions
 Juliet+0.033
 Doug+0.033
ox+0.032
 broom+0.032
 Donna+0.031
Neg logit contributions
 cand-0.036
rell-0.031
 candy-0.030
 sweets-0.030
 bamboo-0.030
Token tree
Token ID5509
Feature activation+9.28e-03

Pos logit contributions
 cand+0.053
rell+0.047
 sweets+0.045
reating+0.045
 carn+0.042
Neg logit contributions
 broom-0.044
 human-0.042
 Juliet-0.041
 Doug-0.040
 stove-0.040
Token!
Token ID0
Feature activation-1.17e-02

Pos logit contributions
 cand+0.016
rell+0.013
 sweets+0.013
 candy+0.012
 bamboo+0.012
Neg logit contributions
 Juliet-0.016
 Doug-0.016
icker-0.016
 Donna-0.016
 broom-0.015
Token Jane
Token ID12091
Feature activation+6.92e-03

Pos logit contributions
 Juliet+0.020
 Doug+0.020
icker+0.020
avi+0.019
ox+0.019
Neg logit contributions
 cand-0.020
rell-0.017
 sweets-0.017
 candy-0.016
 bamboo-0.016
Token saw
Token ID2497
Feature activation+1.06e-02

Pos logit contributions
 cand+0.013
rell+0.011
 sweets+0.011
 candy+0.011
reating+0.011
Neg logit contributions
 Juliet-0.011
 Doug-0.011
icker-0.010
ox-0.010
 Donna-0.010
Token lots
Token ID6041
Feature activation+7.18e-02

Pos logit contributions
 cand+0.021
rell+0.018
 sweets+0.017
 bamboo+0.017
 carn+0.017
Neg logit contributions
 Juliet-0.016
 Doug-0.015
 Donna-0.015
icker-0.015
 broom-0.015
Token of
Token ID286
Feature activation+9.21e-02

Pos logit contributions
 carn+0.124
rell+0.123
 cand+0.122
 coaster+0.121
brate+0.115
Neg logit contributions
 insect-0.093
 human-0.093
 broom-0.088
 Judy-0.082
 pots-0.080
Token p
Token ID279
Feature activation+2.00e-02

Pos logit contributions
orting+0.182
rell+0.181
ousel+0.177
reating+0.175
seek+0.175
Neg logit contributions
 pots-0.105
 broom-0.095
 knob-0.093
 insect-0.091
 curious-0.090
Tokenears
Token ID4127
Feature activation+2.06e-02

Pos logit contributions
 cand+0.031
 sweets+0.026
rell+0.025
 candy+0.025
 carn+0.024
Neg logit contributions
icker-0.038
 Juliet-0.037
ox-0.036
Jud-0.036
 Donna-0.035
Token hanging
Token ID10938
Feature activation+2.18e-02

Pos logit contributions
 cand+0.036
rell+0.031
 sweets+0.030
 carn+0.029
 candy+0.028
Neg logit contributions
 broom-0.032
 Juliet-0.032
 Donna-0.032
 Doug-0.031
icker-0.031
Token,
Token ID11
Feature activation+2.34e-02

Pos logit contributions
 cand+0.033
 sweets+0.027
rell+0.027
 carn+0.027
 candy+0.025
Neg logit contributions
 Juliet-0.040
 Doug-0.039
 broom-0.039
icker-0.039
 Donna-0.039
Token so
Token ID523
Feature activation-6.14e-03

Pos logit contributions
 cand+0.041
rell+0.036
 sweets+0.033
reating+0.033
 carn+0.033
Neg logit contributions
 Juliet-0.037
 broom-0.037
 Doug-0.036
 Donna-0.035
 human-0.035
Token candy
Token ID18550
Feature activation+1.19e-02

Pos logit contributions
 cand+0.072
rell+0.072
 course+0.063
hell+0.063
reating+0.063
Neg logit contributions
 broom-0.050
 stove-0.048
 tool-0.046
 human-0.045
 pots-0.042
Token jar
Token ID17379
Feature activation-4.11e-03

Pos logit contributions
 cand+0.020
rell+0.018
 sweets+0.017
 bamboo+0.016
 candy+0.015
Neg logit contributions
 Juliet-0.020
 broom-0.020
icker-0.020
 Doug-0.020
 human-0.020
Token and
Token ID290
Feature activation+3.69e-03

Pos logit contributions
 Juliet+0.008
 Doug+0.007
icker+0.007
 Donna+0.007
avi+0.007
Neg logit contributions
 cand-0.007
rell-0.006
 sweets-0.006
 candy-0.005
 bamboo-0.005
Token ate
Token ID15063
Feature activation+5.12e-02

Pos logit contributions
 cand+0.006
rell+0.006
 sweets+0.005
 candy+0.005
 bamboo+0.005
Neg logit contributions
 Juliet-0.006
 Doug-0.006
icker-0.006
 Donna-0.006
 broom-0.006
Token too
Token ID1165
Feature activation+1.86e-02

Pos logit contributions
rell+0.112
 carn+0.103
ogging+0.102
 cand+0.102
reating+0.100
Neg logit contributions
 stove-0.050
 pots-0.047
 broom-0.044
kins-0.043
 Doug-0.043
Token much
Token ID881
Feature activation+9.21e-02

Pos logit contributions
 cand+0.028
rell+0.024
 sweets+0.022
 carn+0.022
reating+0.020
Neg logit contributions
icker-0.036
 Juliet-0.035
 broom-0.034
 Doug-0.034
 human-0.034
Token candy
Token ID18550
Feature activation+2.23e-02

Pos logit contributions
rol+0.114
 carn+0.112
ousel+0.111
ieved+0.102
|+0.102
Neg logit contributions
 tool-0.154
 pots-0.152
 broom-0.149
 knife-0.146
 human-0.143
Token.
Token ID13
Feature activation+1.58e-02

Pos logit contributions
 cand+0.042
rell+0.039
 sweets+0.037
 bamboo+0.036
 carn+0.036
Neg logit contributions
icker-0.030
 broom-0.029
 Juliet-0.029
 Doug-0.029
avi-0.028
Token His
Token ID2399
Feature activation+2.93e-02

Pos logit contributions
 cand+0.028
 sweets+0.023
rell+0.023
reating+0.022
 bamboo+0.022
Neg logit contributions
 Doug-0.027
 Juliet-0.026
icker-0.026
 Donna-0.026
 Judy-0.025
Token tum
Token ID11814
Feature activation+4.29e-02

Pos logit contributions
rell+0.074
 cand+0.073
reating+0.070
 carn+0.068
 course+0.068
Neg logit contributions
 human-0.021
 broom-0.021
ox-0.019
 tool-0.019
icker-0.018
Tokenmy
Token ID1820
Feature activation+4.24e-02

Pos logit contributions
 cand+0.068
 carn+0.057
 sweets+0.057
 bamboo+0.054
 candy+0.051
Neg logit contributions
ox-0.076
icker-0.075
 Juliet-0.073
 Doug-0.073
cker-0.072
Tokenumpy
Token ID32152
Feature activation+2.52e-02

Pos logit contributions
 Juliet+0.018
 Doug+0.018
icker+0.017
 broom+0.017
 Donna+0.017
Neg logit contributions
 cand-0.021
rell-0.018
 sweets-0.017
 bamboo-0.017
 candy-0.017
Token elephant
Token ID20950
Feature activation+1.07e-02

Pos logit contributions
 cand+0.052
 sweets+0.046
rell+0.045
reating+0.043
 candy+0.042
Neg logit contributions
 human-0.034
 Juliet-0.034
 Donna-0.034
 Doug-0.033
icker-0.033
Token named
Token ID3706
Feature activation+8.03e-03

Pos logit contributions
 cand+0.020
rell+0.017
 sweets+0.017
 candy+0.016
reating+0.016
Neg logit contributions
 Juliet-0.017
icker-0.017
 Doug-0.017
ox-0.016
 human-0.016
Token Ell
Token ID7122
Feature activation-2.98e-02

Pos logit contributions
 cand+0.014
rell+0.011
 sweets+0.011
 candy+0.011
 bamboo+0.010
Neg logit contributions
 Juliet-0.014
 Doug-0.014
 Donna-0.014
icker-0.014
ox-0.013
Tokeny
Token ID88
Feature activation+4.79e-03

Pos logit contributions
 Doug+0.031
 Juliet+0.030
 Donna+0.029
 broom+0.027
 Judy+0.025
Neg logit contributions
 cand-0.074
rell-0.064
reating-0.063
 bamboo-0.063
 sweets-0.062
Token.
Token ID13
Feature activation+9.15e-02

Pos logit contributions
 cand+0.009
rell+0.008
 sweets+0.008
 candy+0.007
 bamboo+0.007
Neg logit contributions
 Juliet-0.007
 Doug-0.007
icker-0.007
 Donna-0.007
ox-0.007
Token Ell
Token ID7122
Feature activation-2.32e-02

Pos logit contributions
 cand+0.162
 course+0.158
ieved+0.153
orting+0.149
reating+0.149
Neg logit contributions
 Mir-0.099
 Jess-0.099
 maj-0.098
 Karl-0.096
 dunno-0.093
Tokeny
Token ID88
Feature activation+1.91e-02

Pos logit contributions
 Doug+0.029
 Juliet+0.029
 Donna+0.027
 broom+0.027
icker+0.026
Neg logit contributions
 cand-0.052
rell-0.044
 sweets-0.043
 bamboo-0.043
hell-0.042
Token had
Token ID550
Feature activation-1.28e-02

Pos logit contributions
 cand+0.034
rell+0.029
 sweets+0.029
reating+0.028
 candy+0.027
Neg logit contributions
 Juliet-0.032
 Doug-0.031
ox-0.031
 human-0.031
avi-0.031
Token a
Token ID257
Feature activation-3.10e-02

Pos logit contributions
 Juliet+0.022
icker+0.022
 Doug+0.021
avi+0.021
 Donna+0.020
Neg logit contributions
 cand-0.023
 sweets-0.019
 candy-0.019
rell-0.019
 bamboo-0.019
Token long
Token ID890
Feature activation-6.58e-03

Pos logit contributions
 Juliet+0.055
 Doug+0.052
avi+0.052
icker+0.052
Jud+0.051
Neg logit contributions
 cand-0.055
 candy-0.048
 sweets-0.046
 bamboo-0.045
 carn-0.042
Token.
Token ID13
Feature activation+1.31e-02

Pos logit contributions
 cand+0.056
rell+0.049
 sweets+0.047
 bamboo+0.045
reating+0.044
Neg logit contributions
 Juliet-0.056
 Doug-0.056
 human-0.055
 broom-0.054
avi-0.054
Token Now
Token ID2735
Feature activation+4.92e-02

Pos logit contributions
 cand+0.023
 sweets+0.019
rell+0.018
 candy+0.018
 bamboo+0.018
Neg logit contributions
 Juliet-0.023
 Doug-0.023
 Donna-0.022
icker-0.022
 human-0.021
Token we
Token ID356
Feature activation-8.81e-03

Pos logit contributions
 cand+0.091
rell+0.085
reating+0.082
 carn+0.080
hell+0.077
Neg logit contributions
 Juliet-0.066
 Doug-0.065
 Donna-0.064
 broom-0.063
 Karl-0.062
Token can
Token ID460
Feature activation+1.14e-02

Pos logit contributions
 Juliet+0.015
 Doug+0.014
icker+0.014
 Donna+0.014
avi+0.014
Neg logit contributions
 cand-0.016
rell-0.014
 sweets-0.013
 candy-0.013
 bamboo-0.012
Token buy
Token ID2822
Feature activation+5.43e-02

Pos logit contributions
 cand+0.020
rell+0.017
 sweets+0.017
 candy+0.016
 bamboo+0.016
Neg logit contributions
 Juliet-0.019
icker-0.019
 Doug-0.019
 Donna-0.018
avi-0.018
Token lots
Token ID6041
Feature activation+9.13e-02

Pos logit contributions
rell+0.098
 cand+0.088
ogging+0.087
 carn+0.085
reating+0.082
Neg logit contributions
 Juliet-0.069
 pots-0.069
 Doug-0.069
ox-0.067
 human-0.066
Token of
Token ID286
Feature activation+7.32e-02

Pos logit contributions
rell+0.186
uct+0.168
ieved+0.162
appointed+0.159
Less+0.158
Neg logit contributions
 pots-0.076
 human-0.075
a-0.071
 insect-0.069
as-0.069
Token treats
Token ID18432
Feature activation+2.48e-02

Pos logit contributions
rell+0.148
ogging+0.135
reating+0.127
whe+0.126
ieved+0.124
Neg logit contributions
 pots-0.084
 tool-0.079
 human-0.074
 pans-0.072
ox-0.071
Token!"
Token ID2474
Feature activation+3.89e-02

Pos logit contributions
 cand+0.040
rell+0.037
 sweets+0.033
 carn+0.033
 bamboo+0.033
Neg logit contributions
 Juliet-0.041
icker-0.039
 Doug-0.039
 broom-0.039
avi-0.039
Token
Token ID220
Feature activation+1.97e-03

Pos logit contributions
 cand+0.065
reating+0.060
 carn+0.057
 sweets+0.056
rell+0.053
Neg logit contributions
 Juliet-0.062
 Donna-0.061
 Doug-0.061
 broom-0.061
ox-0.059
Token
Token ID198
Feature activation+3.70e-02

Pos logit contributions
 cand+0.003
rell+0.003
 sweets+0.003
 candy+0.002
 bamboo+0.002
Neg logit contributions
 Juliet-0.004
 Doug-0.004
icker-0.004
 Donna-0.004
ox-0.003
TokenYes
Token ID5297
Feature activation+1.23e-03

Pos logit contributions
 Juliet+0.013
 Doug+0.012
icker+0.012
 broom+0.012
 Donna+0.012
Neg logit contributions
 cand-0.015
 sweets-0.013
rell-0.013
 candy-0.013
 carn-0.012
Token,
Token ID11
Feature activation+2.10e-02

Pos logit contributions
 cand+0.002
rell+0.001
 sweets+0.001
 candy+0.001
 bamboo+0.001
Neg logit contributions
 Juliet-0.003
 Doug-0.003
icker-0.003
 Donna-0.003
 broom-0.003
Token you
Token ID345
Feature activation-6.73e-03

Pos logit contributions
 cand+0.037
rell+0.036
 bamboo+0.031
 carn+0.030
 sweets+0.030
Neg logit contributions
 Juliet-0.033
 Doug-0.032
 Donna-0.032
 broom-0.032
 stove-0.031
Token can
Token ID460
Feature activation+2.60e-02

Pos logit contributions
 Juliet+0.010
icker+0.010
 Doug+0.010
 Donna+0.010
avi+0.010
Neg logit contributions
 cand-0.013
 sweets-0.011
rell-0.011
 candy-0.011
 bamboo-0.010
Token have
Token ID423
Feature activation+7.17e-02

Pos logit contributions
 cand+0.045
rell+0.039
 bamboo+0.037
reating+0.037
 sweets+0.037
Neg logit contributions
icker-0.042
 Juliet-0.040
 Doug-0.040
avi-0.039
 Donna-0.039
Token some
Token ID617
Feature activation+9.09e-02

Pos logit contributions
rell+0.136
ogging+0.125
whe+0.124
reating+0.122
rol+0.122
Neg logit contributions
 pots-0.072
 dad-0.070
 tool-0.069
 human-0.066
 Mother-0.065
Token candy
Token ID18550
Feature activation+1.26e-02

Pos logit contributions
rell+0.111
|+0.099
rol+0.098
rob+0.096
ousel+0.095
Neg logit contributions
 tool-0.157
 pots-0.155
 stove-0.145
 scissors-0.143
 knife-0.143
Token."
Token ID526
Feature activation+2.38e-02

Pos logit contributions
 cand+0.021
rell+0.018
 sweets+0.017
 bamboo+0.016
 candy+0.016
Neg logit contributions
 Juliet-0.022
icker-0.021
 Doug-0.021
 broom-0.021
 Donna-0.021
Token The
Token ID383
Feature activation+2.43e-02

Pos logit contributions
 cand+0.044
rell+0.038
 bamboo+0.037
 sweets+0.037
reating+0.037
Neg logit contributions
 Juliet-0.038
icker-0.036
 Judy-0.035
 Doug-0.035
 Donna-0.034
Token nice
Token ID3621
Feature activation+3.47e-02

Pos logit contributions
rell+0.051
 cand+0.050
reating+0.045
 bamboo+0.044
 carn+0.042
Neg logit contributions
 human-0.029
 stove-0.029
 broom-0.028
icker-0.027
 father-0.026
Token little
Token ID1310
Feature activation+3.93e-03

Pos logit contributions
rell+0.065
 cand+0.061
 bamboo+0.055
reating+0.055
 carn+0.054
Neg logit contributions
 human-0.048
 stove-0.048
 Juliet-0.046
 broom-0.046
 tool-0.045
Token there
Token ID612
Feature activation+1.68e-02

Pos logit contributions
 Juliet+0.027
avi+0.026
 Doug+0.026
 Donna+0.025
icker+0.025
Neg logit contributions
 cand-0.024
 sweets-0.021
 bamboo-0.020
 candy-0.020
rell-0.020
Token was
Token ID373
Feature activation-3.91e-03

Pos logit contributions
 cand+0.031
rell+0.026
 sweets+0.026
reating+0.025
 candy+0.024
Neg logit contributions
 Juliet-0.027
 Doug-0.027
icker-0.027
 Donna-0.026
 human-0.025
Token a
Token ID257
Feature activation-2.36e-02

Pos logit contributions
 Juliet+0.006
 Doug+0.006
icker+0.006
 Donna+0.006
avi+0.005
Neg logit contributions
 cand-0.008
rell-0.007
 sweets-0.007
 candy-0.006
 bamboo-0.006
Token sheet
Token ID9629
Feature activation+7.70e-03

Pos logit contributions
 Juliet+0.041
 Doug+0.040
 Donna+0.039
Jud+0.038
icker+0.038
Neg logit contributions
 cand-0.041
 candy-0.036
 sweets-0.034
 bamboo-0.034
 carn-0.032
Token.
Token ID13
Feature activation-1.64e-03

Pos logit contributions
 cand+0.014
rell+0.012
 sweets+0.012
 candy+0.011
 bamboo+0.011
Neg logit contributions
 Juliet-0.013
icker-0.013
 Doug-0.013
 Donna-0.012
 broom-0.012
Token This
Token ID770
Feature activation-1.08e-01

Pos logit contributions
 Juliet+0.003
 Doug+0.003
icker+0.003
 Donna+0.003
ox+0.003
Neg logit contributions
 cand-0.003
rell-0.002
 sweets-0.002
 candy-0.002
 bamboo-0.002
Token sheet
Token ID9629
Feature activation+9.93e-03

Pos logit contributions
cker+0.179
Jud+0.178
ierce+0.173
avi+0.173
 brigade+0.168
Neg logit contributions
 cand-0.158
 more-0.156
 candy-0.155
 again-0.143
 nap-0.143
Token could
Token ID714
Feature activation-4.49e-02

Pos logit contributions
 cand+0.016
rell+0.014
 sweets+0.014
 candy+0.013
reating+0.013
Neg logit contributions
 Juliet-0.018
 Doug-0.017
icker-0.017
 Donna-0.017
 broom-0.017
Token talk
Token ID1561
Feature activation+7.04e-03

Pos logit contributions
 Juliet+0.087
 Doug+0.086
 Donna+0.084
Jud+0.084
avi+0.083
Neg logit contributions
 cand-0.066
 bamboo-0.055
 candy-0.055
rell-0.054
 sweets-0.053
Token.
Token ID13
Feature activation+7.48e-03

Pos logit contributions
 cand+0.012
rell+0.010
 sweets+0.010
 candy+0.009
 bamboo+0.009
Neg logit contributions
 Juliet-0.012
 Doug-0.012
icker-0.012
 Donna-0.011
 broom-0.011
Token All
Token ID1439
Feature activation-2.62e-02

Pos logit contributions
 cand+0.014
rell+0.012
 sweets+0.012
 candy+0.012
 bamboo+0.011
Neg logit contributions
 Juliet-0.012
 Doug-0.011
icker-0.011
 Donna-0.011
 broom-0.011
Token Just
Token ID2329
Feature activation+3.46e-03

Pos logit contributions
 cand+0.013
rell+0.012
 sweets+0.011
 candy+0.011
reating+0.011
Neg logit contributions
 Juliet-0.011
 Doug-0.011
icker-0.010
 Donna-0.010
avi-0.010
Token then
Token ID788
Feature activation+3.40e-03

Pos logit contributions
 cand+0.005
rell+0.004
 sweets+0.004
 candy+0.004
 bamboo+0.004
Neg logit contributions
 Juliet-0.007
 Doug-0.007
icker-0.007
 Donna-0.007
ox-0.007
Token,
Token ID11
Feature activation-3.49e-03

Pos logit contributions
 cand+0.004
rell+0.003
 sweets+0.003
 candy+0.003
 bamboo+0.003
Neg logit contributions
 Juliet-0.008
 Doug-0.007
icker-0.007
 Donna-0.007
avi-0.007
Token a
Token ID257
Feature activation-1.13e-02

Pos logit contributions
 Juliet+0.005
icker+0.005
 Doug+0.005
 Donna+0.005
ox+0.005
Neg logit contributions
 cand-0.007
rell-0.006
 sweets-0.006
 candy-0.006
 bamboo-0.005
Token chip
Token ID11594
Feature activation+1.10e-02

Pos logit contributions
 Juliet+0.016
icker+0.016
 Doug+0.016
ox+0.016
avi+0.016
Neg logit contributions
 cand-0.022
 sweets-0.019
 candy-0.019
rell-0.019
 bamboo-0.018
Tokenm
Token ID76
Feature activation-1.02e-01

Pos logit contributions
 cand+0.017
rell+0.015
 sweets+0.015
 candy+0.014
 carn+0.013
Neg logit contributions
 Juliet-0.020
 Doug-0.020
icker-0.020
 broom-0.020
 human-0.020
Tokenunk
Token ID2954
Feature activation-8.81e-03

Pos logit contributions
 Juliet+0.126
 brigade+0.122
Jud+0.115
 basement+0.113
 pans+0.112
Neg logit contributions
 cand-0.182
hell-0.177
rell-0.172
que-0.166
 ac-0.154
Token named
Token ID3706
Feature activation-1.70e-02

Pos logit contributions
 Juliet+0.015
icker+0.015
 Doug+0.014
avi+0.014
 Donna+0.014
Neg logit contributions
 cand-0.015
rell-0.013
 sweets-0.013
 candy-0.012
 bamboo-0.012
Token Sam
Token ID3409
Feature activation-4.88e-03

Pos logit contributions
icker+0.031
 Juliet+0.030
ox+0.029
avi+0.029
 broom+0.029
Neg logit contributions
 cand-0.028
rell-0.024
 sweets-0.023
 candy-0.023
 bamboo-0.022
Token came
Token ID1625
Feature activation-2.41e-02

Pos logit contributions
 Juliet+0.009
icker+0.009
 Doug+0.008
 Donna+0.008
avi+0.008
Neg logit contributions
 cand-0.008
rell-0.007
 sweets-0.007
 candy-0.007
 bamboo-0.006
Token by
Token ID416
Feature activation-1.49e-02

Pos logit contributions
icker+0.047
 Juliet+0.046
avi+0.046
ox+0.044
 Doug+0.044
Neg logit contributions
 cand-0.033
rell-0.030
 sweets-0.028
 bamboo-0.028
 again-0.027
Token
Token ID6184
Feature activation-3.82e-02

Pos logit contributions
 cand+0.034
rell+0.029
 sweets+0.029
 candy+0.027
 bamboo+0.027
Neg logit contributions
 Juliet-0.032
 Doug-0.031
icker-0.031
 human-0.031
 broom-0.031
Token
Token ID95
Feature activation-3.93e-02

Pos logit contributions
 Juliet+0.066
Jud+0.062
 broom+0.062
 Doug+0.062
ox+0.060
Neg logit contributions
 cand-0.065
rell-0.058
 carn-0.055
 candy-0.055
 sweets-0.054
Token
Token ID26391
Feature activation-8.20e-02

Pos logit contributions
 Juliet+0.071
 broom+0.070
 Doug+0.068
icker+0.068
 Donna+0.067
Neg logit contributions
 cand-0.061
rell-0.058
 carn-0.053
 candy-0.049
 course-0.049
Token
Token ID447
Feature activation+8.45e-03

Pos logit contributions
 Juliet+0.148
 Donna+0.148
icker+0.144
 weed+0.142
 Doug+0.142
Neg logit contributions
 cand-0.113
rell-0.107
 carn-0.092
 candy-0.091
hell-0.090
Token
Token ID250
Feature activation+1.38e-02

Pos logit contributions
 cand+0.015
rell+0.013
 sweets+0.013
 candy+0.012
 bamboo+0.012
Neg logit contributions
 Juliet-0.014
icker-0.014
 Doug-0.013
avi-0.013
 Donna-0.013
Token which
Token ID543
Feature activation-9.67e-02

Pos logit contributions
 cand+0.027
rell+0.023
 sweets+0.023
 candy+0.022
 bamboo+0.021
Neg logit contributions
 Juliet-0.021
 Doug-0.020
icker-0.020
avi-0.020
Jud-0.019
Token he
Token ID339
Feature activation-1.80e-02

Pos logit contributions
icker+0.204
Jud+0.181
Rachel+0.181
zzy+0.176
sing+0.175
Neg logit contributions
 course-0.134
 candy-0.134
 cand-0.131
rell-0.131
 sweets-0.119
Token loved
Token ID6151
Feature activation+2.05e-03

Pos logit contributions
 Juliet+0.031
icker+0.031
Jud+0.030
 Doug+0.030
 Donna+0.029
Neg logit contributions
 cand-0.032
rell-0.027
 sweets-0.027
 candy-0.026
 bamboo-0.025
Token to
Token ID284
Feature activation-2.55e-02

Pos logit contributions
 cand+0.004
rell+0.004
 sweets+0.004
 candy+0.003
 bamboo+0.003
Neg logit contributions
 Juliet-0.003
 Doug-0.003
icker-0.003
 Donna-0.003
 broom-0.003
Token drive
Token ID3708
Feature activation+3.78e-03

Pos logit contributions
 Juliet+0.050
 Doug+0.048
Jud+0.047
icker+0.047
 Donna+0.047
Neg logit contributions
 cand-0.039
rell-0.034
 sweets-0.033
 candy-0.033
 bamboo-0.031
Token!
Token ID0
Feature activation+2.86e-02

Pos logit contributions
 cand+0.006
rell+0.005
 sweets+0.005
 candy+0.005
 bamboo+0.005
Neg logit contributions
 Juliet-0.007
 Doug-0.007
icker-0.007
 Donna-0.006
ox-0.006
Token drum
Token ID13026
Feature activation+7.33e-03

Pos logit contributions
Jud+0.080
avi+0.078
 Juliet+0.076
ox+0.075
 Judy+0.075
Neg logit contributions
 cand-0.073
 candy-0.071
 sweets-0.063
 carn-0.062
 bamboo-0.059
Token and
Token ID290
Feature activation-3.68e-02

Pos logit contributions
 cand+0.011
rell+0.009
 sweets+0.009
 candy+0.009
 bamboo+0.009
Neg logit contributions
 Juliet-0.014
 Doug-0.014
icker-0.014
 broom-0.013
 Donna-0.013
Token Mia
Token ID32189
Feature activation-1.43e-02

Pos logit contributions
icker+0.069
Jud+0.064
cker+0.063
 Juliet+0.062
 Donna+0.061
Neg logit contributions
 cand-0.061
 candy-0.053
 sweets-0.051
rell-0.048
 bamboo-0.048
Token has
Token ID468
Feature activation-3.69e-02

Pos logit contributions
 Juliet+0.025
icker+0.024
 Doug+0.024
Jud+0.024
 Donna+0.024
Neg logit contributions
 cand-0.024
rell-0.021
 sweets-0.020
 candy-0.020
 bamboo-0.019
Token a
Token ID257
Feature activation-6.00e-02

Pos logit contributions
icker+0.071
kins+0.067
cker+0.067
 Donna+0.066
icia+0.066
Neg logit contributions
 cand-0.056
 candy-0.049
rell-0.048
 sweets-0.048
 bamboo-0.044
Token fl
Token ID781
Feature activation-9.33e-02

Pos logit contributions
avi+0.107
Jud+0.107
 Judy+0.102
 Juliet+0.102
icia+0.100
Neg logit contributions
 cand-0.094
 candy-0.092
 sweets-0.082
 carn-0.079
 bamboo-0.077
Tokenute
Token ID1133
Feature activation-2.59e-02

Pos logit contributions
Jud+0.183
 Judy+0.176
 Donna+0.170
 Doug+0.166
icia+0.162
Neg logit contributions
ogging-0.112
oot-0.101
 cand-0.100
 medal-0.098
rell-0.095
Token.
Token ID13
Feature activation-2.12e-02

Pos logit contributions
 Juliet+0.050
Jud+0.050
 Doug+0.049
icker+0.049
 Donna+0.048
Neg logit contributions
 cand-0.040
rell-0.033
 candy-0.032
 sweets-0.032
 bamboo-0.031
Token They
Token ID1119
Feature activation-2.49e-02

Pos logit contributions
 broom+0.036
icker+0.035
ox+0.035
 Juliet+0.035
cker+0.035
Neg logit contributions
 cand-0.035
rell-0.031
 bamboo-0.030
 sweets-0.029
 candy-0.029
Token make
Token ID787
Feature activation-3.49e-02

Pos logit contributions
 Juliet+0.046
Jud+0.045
icker+0.045
 Doug+0.045
 Donna+0.044
Neg logit contributions
 cand-0.038
rell-0.034
 sweets-0.032
 candy-0.031
 bamboo-0.029
Token different
Token ID1180
Feature activation-7.29e-03

Pos logit contributions
Jud+0.066
cker+0.065
 Donna+0.064
icker+0.064
 Juliet+0.063
Neg logit contributions
 cand-0.052
rell-0.043
 candy-0.043
 sweets-0.042
 bamboo-0.041
Token the
Token ID262
Feature activation-2.26e-02

Pos logit contributions
ox+0.069
 Juliet+0.067
cker+0.065
avi+0.065
icia+0.065
Neg logit contributions
 cand-0.048
 again-0.042
 candy-0.041
 sweets-0.040
 course-0.038
Token fire
Token ID2046
Feature activation-4.36e-02

Pos logit contributions
 Juliet+0.033
Jud+0.031
 Donna+0.030
 Doug+0.030
icker+0.030
Neg logit contributions
 cand-0.047
rell-0.041
 sweets-0.041
 candy-0.040
 bamboo-0.040
Token.
Token ID13
Feature activation-1.19e-02

Pos logit contributions
 Juliet+0.086
Jud+0.084
 Donna+0.081
icia+0.079
 dunno+0.079
Neg logit contributions
 cand-0.067
rell-0.057
 sweets-0.052
 candy-0.052
 bamboo-0.052
Token The
Token ID383
Feature activation-2.56e-02

Pos logit contributions
 Juliet+0.021
icker+0.021
ox+0.020
 broom+0.020
avi+0.020
Neg logit contributions
 cand-0.019
rell-0.017
 sweets-0.016
 candy-0.016
 bamboo-0.015
Token marsh
Token ID22397
Feature activation-2.50e-02

Pos logit contributions
 Juliet+0.042
ox+0.040
Jud+0.040
 Donna+0.039
 Doug+0.038
Neg logit contributions
 cand-0.049
 sweets-0.042
 bamboo-0.042
rell-0.041
 candy-0.041
Tokenm
Token ID76
Feature activation-9.31e-02

Pos logit contributions
 Juliet+0.053
ox+0.050
 Doug+0.050
 Donna+0.050
 broom+0.050
Neg logit contributions
 cand-0.034
rell-0.027
 sweets-0.027
 candy-0.025
 course-0.025
Tokenallows
Token ID47205
Feature activation+1.77e-03

Pos logit contributions
Jud+0.141
 Juliet+0.136
iane+0.128
Rachel+0.127
 Doug+0.126
Neg logit contributions
rell-0.163
 cand-0.163
 about-0.150
 bamboo-0.144
 sweets-0.137
Token became
Token ID2627
Feature activation-2.20e-02

Pos logit contributions
 cand+0.002
rell+0.002
 sweets+0.002
 candy+0.002
 bamboo+0.002
Neg logit contributions
 Juliet-0.004
 Doug-0.004
icker-0.004
 Donna-0.003
 broom-0.003
Token all
Token ID477
Feature activation-6.10e-03

Pos logit contributions
ox+0.043
 Juliet+0.042
icker+0.042
avi+0.042
 Doug+0.041
Neg logit contributions
 cand-0.034
 sweets-0.028
 candy-0.028
rell-0.027
 bamboo-0.027
Token warm
Token ID5814
Feature activation-3.27e-03

Pos logit contributions
 Juliet+0.011
 Doug+0.011
icker+0.011
ox+0.011
 Donna+0.011
Neg logit contributions
 cand-0.010
rell-0.009
 sweets-0.008
 candy-0.008
 bamboo-0.008
Token and
Token ID290
Feature activation-1.63e-02

Pos logit contributions
 Juliet+0.006
 Doug+0.006
icker+0.006
 Donna+0.006
ox+0.006
Neg logit contributions
 cand-0.005
rell-0.004
 sweets-0.004
 candy-0.004
 bamboo-0.004
Token there
Token ID612
Feature activation+1.16e-02

Pos logit contributions
 Juliet+0.037
avi+0.035
 Doug+0.035
 Donna+0.034
Jud+0.034
Neg logit contributions
 cand-0.029
 bamboo-0.024
 candy-0.024
 sweets-0.024
rell-0.024
Token was
Token ID373
Feature activation-1.38e-02

Pos logit contributions
 cand+0.020
rell+0.017
 sweets+0.017
 candy+0.016
reating+0.016
Neg logit contributions
 Juliet-0.020
 Doug-0.020
icker-0.019
 Donna-0.019
 human-0.019
Token a
Token ID257
Feature activation-3.05e-02

Pos logit contributions
 Juliet+0.023
 Doug+0.022
icker+0.022
avi+0.022
 Donna+0.022
Neg logit contributions
 cand-0.025
 sweets-0.021
 candy-0.021
rell-0.021
 bamboo-0.021
Token sheep
Token ID15900
Feature activation+9.38e-03

Pos logit contributions
 Juliet+0.054
 Doug+0.052
 Donna+0.051
Jud+0.050
ox+0.050
Neg logit contributions
 cand-0.053
 candy-0.046
 sweets-0.044
 bamboo-0.043
 carn-0.041
Token.
Token ID13
Feature activation-8.75e-03

Pos logit contributions
 cand+0.017
rell+0.015
 sweets+0.015
 candy+0.014
reating+0.013
Neg logit contributions
 Juliet-0.015
icker-0.015
 Doug-0.015
 Donna-0.015
ox-0.015
Token This
Token ID770
Feature activation-8.95e-02

Pos logit contributions
 Juliet+0.016
icker+0.016
 Doug+0.016
 Donna+0.015
ox+0.015
Neg logit contributions
 cand-0.014
rell-0.012
 sweets-0.012
 candy-0.011
 bamboo-0.011
Token sheep
Token ID15900
Feature activation+2.79e-02

Pos logit contributions
icker+0.154
sing+0.148
 Doug+0.144
Jud+0.142
 Scott+0.140
Neg logit contributions
 bamboo-0.135
 cand-0.134
rell-0.132
 l-0.127
 candy-0.123
Token was
Token ID373
Feature activation-8.77e-03

Pos logit contributions
 cand+0.052
reating+0.046
rell+0.046
 sweets+0.045
 candy+0.042
Neg logit contributions
 Juliet-0.042
 Doug-0.041
 human-0.041
icker-0.040
 Donna-0.040
Token very
Token ID845
Feature activation-2.27e-02

Pos logit contributions
 Juliet+0.015
icker+0.015
 Doug+0.015
ox+0.015
avi+0.015
Neg logit contributions
 cand-0.015
rell-0.013
 sweets-0.012
 candy-0.012
 bamboo-0.012
Token sad
Token ID6507
Feature activation-3.38e-03

Pos logit contributions
 Juliet+0.041
 Doug+0.041
ox+0.039
 broom+0.039
Jud+0.039
Neg logit contributions
 cand-0.038
 bamboo-0.032
 candy-0.031
rell-0.031
 sweets-0.031
Token.
Token ID13
Feature activation-9.14e-04

Pos logit contributions
 Juliet+0.006
 Doug+0.006
icker+0.006
 Donna+0.005
Jud+0.005
Neg logit contributions
 cand-0.006
rell-0.005
 sweets-0.005
 candy-0.005
 bamboo-0.005
Token was
Token ID373
Feature activation-1.49e-02

Pos logit contributions
 cand+0.000
rell+0.000
 sweets+0.000
 candy+0.000
 bamboo+0.000
Neg logit contributions
 Juliet-0.001
 Doug-0.001
icker-0.001
 Donna-0.001
ox-0.001
Token an
Token ID281
Feature activation+1.26e-03

Pos logit contributions
 Juliet+0.024
 Doug+0.024
icker+0.023
 Donna+0.023
avi+0.023
Neg logit contributions
 cand-0.027
 sweets-0.023
rell-0.023
 candy-0.023
 bamboo-0.022
Token enormous
Token ID9812
Feature activation+1.70e-02

Pos logit contributions
 cand+0.002
rell+0.002
 sweets+0.002
 candy+0.002
 bamboo+0.002
Neg logit contributions
 Juliet-0.002
icker-0.002
 Doug-0.002
 Donna-0.002
ox-0.002
Token drum
Token ID13026
Feature activation+1.15e-02

Pos logit contributions
 cand+0.035
rell+0.031
 sweets+0.030
reating+0.028
 candy+0.028
Neg logit contributions
 Juliet-0.024
 human-0.023
 broom-0.023
 Doug-0.023
icker-0.023
Token.
Token ID13
Feature activation+6.35e-03

Pos logit contributions
 cand+0.021
 sweets+0.018
rell+0.018
 candy+0.017
 bamboo+0.017
Neg logit contributions
 Juliet-0.018
icker-0.018
 Doug-0.018
 broom-0.018
 human-0.018
Token This
Token ID770
Feature activation-8.81e-02

Pos logit contributions
 cand+0.012
 sweets+0.010
rell+0.010
 candy+0.010
 bamboo+0.010
Neg logit contributions
 Juliet-0.010
 Doug-0.010
icker-0.009
 Donna-0.009
avi-0.009
Token drum
Token ID13026
Feature activation+1.61e-02

Pos logit contributions
avi+0.166
Jud+0.164
apa+0.158
cker+0.155
icker+0.154
Neg logit contributions
rell-0.115
 course-0.111
 coaster-0.110
 candy-0.101
 marble-0.099
Token lived
Token ID5615
Feature activation+3.97e-03

Pos logit contributions
 cand+0.028
 sweets+0.024
rell+0.023
reating+0.023
 candy+0.022
Neg logit contributions
 Juliet-0.027
 Doug-0.027
icker-0.026
 human-0.026
 Donna-0.026
Token in
Token ID287
Feature activation-3.43e-02

Pos logit contributions
 cand+0.007
rell+0.006
 sweets+0.006
 candy+0.006
 bamboo+0.005
Neg logit contributions
 Juliet-0.007
icker-0.007
 Doug-0.007
 broom-0.006
 Donna-0.006
Token a
Token ID257
Feature activation-1.87e-02

Pos logit contributions
icker+0.072
cker+0.068
avi+0.067
 brigade+0.066
Jud+0.066
Neg logit contributions
 cand-0.045
 candy-0.039
rell-0.039
 course-0.039
 bamboo-0.038
Token big
Token ID1263
Feature activation-4.28e-03

Pos logit contributions
 Juliet+0.028
 Doug+0.027
 Donna+0.027
avi+0.027
icker+0.027
Neg logit contributions
 cand-0.036
 candy-0.031
rell-0.031
 sweets-0.031
 bamboo-0.030
Token.
Token ID13
Feature activation-3.21e-02

Pos logit contributions
 Juliet+0.099
 Doug+0.097
Jud+0.096
icker+0.096
 Donna+0.095
Neg logit contributions
 cand-0.063
 sweets-0.050
 candy-0.049
rell-0.048
 again-0.043
Token They
Token ID1119
Feature activation-3.56e-02

Pos logit contributions
cker+0.058
ox+0.058
avi+0.056
 Juliet+0.056
 broom+0.056
Neg logit contributions
 cand-0.050
rell-0.042
 candy-0.042
 sweets-0.040
 bamboo-0.039
Token used
Token ID973
Feature activation-3.60e-02

Pos logit contributions
 Juliet+0.065
 Donna+0.064
icker+0.063
 Doug+0.062
ox+0.061
Neg logit contributions
 cand-0.059
 sweets-0.048
 candy-0.046
rell-0.045
 carn-0.042
Token a
Token ID257
Feature activation-3.67e-02

Pos logit contributions
 Juliet+0.065
avi+0.064
icker+0.064
icia+0.062
 Donna+0.062
Neg logit contributions
 cand-0.062
 sweets-0.052
 candy-0.052
rell-0.049
 bamboo-0.047
Token flashlight
Token ID38371
Feature activation-4.52e-02

Pos logit contributions
 Juliet+0.052
avi+0.051
 Donna+0.050
 Doug+0.050
Jud+0.050
Neg logit contributions
 cand-0.075
 candy-0.066
 sweets-0.066
rell-0.061
 bamboo-0.060
Token as
Token ID355
Feature activation-8.69e-02

Pos logit contributions
 Juliet+0.087
Jud+0.087
icker+0.085
avi+0.084
 Donna+0.084
Neg logit contributions
 cand-0.071
 candy-0.058
rell-0.057
 sweets-0.057
 again-0.053
Token the
Token ID262
Feature activation-8.06e-03

Pos logit contributions
ox+0.197
icia+0.194
Jud+0.193
avi+0.189
cker+0.189
Neg logit contributions
 candy-0.095
 cand-0.090
 more-0.080
 sweets-0.078
 better-0.065
Token spotlight
Token ID17838
Feature activation-2.69e-02

Pos logit contributions
 Juliet+0.012
icker+0.012
 Doug+0.012
 Donna+0.012
ox+0.012
Neg logit contributions
 cand-0.016
 sweets-0.013
rell-0.013
 candy-0.013
 bamboo-0.013
Token.
Token ID13
Feature activation-2.93e-02

Pos logit contributions
 Juliet+0.051
Jud+0.051
 Doug+0.050
icker+0.050
 Donna+0.050
Neg logit contributions
 cand-0.042
rell-0.034
 sweets-0.034
 candy-0.033
 bamboo-0.030
Token They
Token ID1119
Feature activation-2.66e-02

Pos logit contributions
cker+0.052
ox+0.051
 Juliet+0.050
avi+0.050
 broom+0.050
Neg logit contributions
 cand-0.046
rell-0.040
 candy-0.039
 sweets-0.037
 bamboo-0.037
Token invited
Token ID9392
Feature activation-9.97e-03

Pos logit contributions
 Juliet+0.047
icker+0.046
 Donna+0.046
 Doug+0.045
ox+0.044
Neg logit contributions
 cand-0.046
 sweets-0.037
rell-0.036
 candy-0.036
 carn-0.034
Token mother
Token ID2802
Feature activation+1.33e-02

Pos logit contributions
 Juliet+0.064
ox+0.063
Jud+0.063
avi+0.063
icker+0.062
Neg logit contributions
 cand-0.091
 candy-0.082
 sweets-0.080
 carn-0.072
 bamboo-0.072
Token's
Token ID338
Feature activation-4.16e-02

Pos logit contributions
 cand+0.022
rell+0.019
 sweets+0.018
 candy+0.017
 bamboo+0.017
Neg logit contributions
 Juliet-0.024
 Doug-0.024
 Donna-0.023
icker-0.023
 broom-0.023
Token:
Token ID25
Feature activation-3.07e-03

Pos logit contributions
 Juliet+0.064
 Doug+0.062
icker+0.061
ox+0.060
avi+0.059
Neg logit contributions
 cand-0.080
 sweets-0.069
 candy-0.069
 carn-0.062
 bamboo-0.060
Token
Token ID6184
Feature activation-2.63e-02

Pos logit contributions
 Juliet+0.005
icker+0.005
 Doug+0.005
 Donna+0.005
ox+0.005
Neg logit contributions
 cand-0.005
rell-0.005
 sweets-0.005
 candy-0.004
 bamboo-0.004
Token
Token ID95
Feature activation-3.78e-02

Pos logit contributions
 broom+0.041
 Doug+0.040
 Juliet+0.040
icker+0.040
ox+0.039
Neg logit contributions
 cand-0.046
rell-0.042
 carn-0.039
 bamboo-0.038
 sweets-0.038
Token
Token ID26391
Feature activation-8.69e-02

Pos logit contributions
icker+0.060
 broom+0.059
 Doug+0.057
kins+0.056
 Juliet+0.055
Neg logit contributions
 cand-0.062
rell-0.062
 carn-0.056
 course-0.055
 sweets-0.052
Token
Token ID129
Feature activation-1.55e-02

Pos logit contributions
cker+0.151
 weed+0.145
icker+0.144
 extingu+0.141
 broom+0.141
Neg logit contributions
rell-0.114
 cand-0.112
 -0.099
 From-0.096
Once-0.095
Token
Token ID241
Feature activation-3.51e-02

Pos logit contributions
 Juliet+0.024
icker+0.024
 Doug+0.023
 broom+0.023
 Donna+0.022
Neg logit contributions
 cand-0.028
rell-0.026
 sweets-0.024
 bamboo-0.024
 carn-0.023
TokenPeter
Token ID19727
Feature activation-2.55e-02

Pos logit contributions
icker+0.064
 broom+0.061
ox+0.060
 Doug+0.060
icia+0.060
Neg logit contributions
 cand-0.054
 sweets-0.047
 candy-0.046
 carn-0.046
rell-0.045
Token,
Token ID11
Feature activation-6.73e-03

Pos logit contributions
icker+0.054
 Juliet+0.053
 Doug+0.051
 broom+0.051
ox+0.051
Neg logit contributions
 cand-0.033
rell-0.027
 sweets-0.026
 candy-0.025
 bamboo-0.024
Token come
Token ID1282
Feature activation-3.13e-02

Pos logit contributions
 Juliet+0.012
icker+0.012
 Doug+0.012
 Donna+0.012
ox+0.012
Neg logit contributions
 cand-0.011
 sweets-0.009
rell-0.009
 candy-0.009
 bamboo-0.008
Token smiled
Token ID13541
Feature activation-3.04e-03

Pos logit contributions
 cand+0.004
rell+0.003
 sweets+0.003
 candy+0.003
 bamboo+0.003
Neg logit contributions
 Juliet-0.004
 Doug-0.004
icker-0.004
 Donna-0.004
 broom-0.004
Token and
Token ID290
Feature activation-6.26e-03

Pos logit contributions
 Juliet+0.006
 Doug+0.005
icker+0.005
 Donna+0.005
ox+0.005
Neg logit contributions
 cand-0.005
rell-0.004
 sweets-0.004
 candy-0.004
 bamboo-0.004
Token said
Token ID531
Feature activation+2.72e-03

Pos logit contributions
 Juliet+0.012
icker+0.012
 Doug+0.012
ox+0.012
avi+0.012
Neg logit contributions
 cand-0.010
 sweets-0.008
rell-0.008
 candy-0.007
 bamboo-0.007
Token
Token ID6184
Feature activation-3.59e-02

Pos logit contributions
 cand+0.004
rell+0.003
 sweets+0.003
 candy+0.003
 bamboo+0.003
Neg logit contributions
 Juliet-0.006
 Doug-0.006
icker-0.006
 Donna-0.006
 broom-0.005
Token
Token ID95
Feature activation-4.22e-02

Pos logit contributions
 Doug+0.056
 broom+0.055
 Juliet+0.054
Jud+0.053
cker+0.052
Neg logit contributions
 cand-0.065
rell-0.055
 sweets-0.053
 carn-0.053
 candy-0.052
Token
Token ID26391
Feature activation-8.68e-02

Pos logit contributions
 broom+0.066
icker+0.066
 Doug+0.065
 tractor+0.064
 Juliet+0.062
Neg logit contributions
 cand-0.069
rell-0.065
 carn-0.061
 course-0.060
 sweets-0.058
Token
Token ID129
Feature activation-2.67e-02

Pos logit contributions
cker+0.159
 extingu+0.142
icker+0.141
 weed+0.139
 ram+0.138
Neg logit contributions
 cand-0.116
 again-0.105
rell-0.104
 From-0.104
 -0.103
Token
Token ID241
Feature activation-5.99e-02

Pos logit contributions
 Juliet+0.040
 Doug+0.040
 broom+0.040
icker+0.040
Jud+0.038
Neg logit contributions
 cand-0.048
rell-0.045
 sweets-0.041
 carn-0.040
 bamboo-0.040
TokenIt
Token ID1026
Feature activation-2.84e-02

Pos logit contributions
icker+0.110
cker+0.110
 tractor+0.110
 broom+0.110
icia+0.106
Neg logit contributions
 cand-0.080
 carn-0.071
 candy-0.071
 sweets-0.070
reating-0.069
Tokenâ
Token ID22940
Feature activation-4.96e-03

Pos logit contributions
icker+0.062
avi+0.060
 Juliet+0.059
ox+0.057
Jud+0.057
Neg logit contributions
 cand-0.038
rell-0.031
 sweets-0.030
 candy-0.029
 bamboo-0.025
Token
Token ID26391
Feature activation-7.99e-02

Pos logit contributions
 Juliet+0.009
 Doug+0.008
icker+0.008
 Donna+0.008
 broom+0.008
Neg logit contributions
 cand-0.009
rell-0.007
 sweets-0.007
 candy-0.007
 bamboo-0.007
Token a
Token ID257
Feature activation-3.28e-02

Pos logit contributions
 Juliet+0.003
 Doug+0.003
icker+0.003
 Donna+0.003
ox+0.003
Neg logit contributions
 cand-0.004
rell-0.004
 sweets-0.004
 candy-0.004
 bamboo-0.004
Token very
Token ID845
Feature activation-2.49e-02

Pos logit contributions
 Juliet+0.058
 Doug+0.057
icker+0.055
 Donna+0.055
ox+0.055
Neg logit contributions
 cand-0.054
 candy-0.047
 bamboo-0.045
 sweets-0.045
 carn-0.042
Token special
Token ID2041
Feature activation-5.04e-03

Pos logit contributions
 Juliet+0.041
 Doug+0.041
ox+0.039
avi+0.039
 Donna+0.039
Neg logit contributions
 cand-0.044
 candy-0.038
 sweets-0.038
 bamboo-0.037
rell-0.036
Token human
Token ID1692
Feature activation-1.60e-03

Pos logit contributions
 Juliet+0.007
 Doug+0.007
icker+0.007
 Donna+0.007
avi+0.007
Neg logit contributions
 cand-0.010
 sweets-0.009
rell-0.009
 candy-0.008
 bamboo-0.008
Token.
Token ID13
Feature activation-1.36e-02

Pos logit contributions
 Juliet+0.003
 Doug+0.003
icker+0.003
 Donna+0.003
ox+0.003
Neg logit contributions
 cand-0.003
rell-0.002
 sweets-0.002
 candy-0.002
 bamboo-0.002
Token This
Token ID770
Feature activation-8.65e-02

Pos logit contributions
 Juliet+0.026
icker+0.026
ox+0.025
 broom+0.025
 Doug+0.025
Neg logit contributions
 cand-0.021
rell-0.018
 sweets-0.017
 candy-0.017
 bamboo-0.016
Token human
Token ID1692
Feature activation+1.47e-02

Pos logit contributions
Jud+0.128
kins+0.121
ances+0.121
chie+0.117
ox+0.113
Neg logit contributions
 candy-0.148
 better-0.142
 more-0.139
 l-0.139
 about-0.138
Token filled
Token ID5901
Feature activation-1.32e-02

Pos logit contributions
 cand+0.025
rell+0.022
 sweets+0.021
reating+0.020
 candy+0.020
Neg logit contributions
 Juliet-0.025
 Doug-0.025
icker-0.024
 Donna-0.024
 human-0.024
Token the
Token ID262
Feature activation-5.91e-03

Pos logit contributions
 Juliet+0.030
icker+0.030
 Doug+0.029
avi+0.029
ox+0.029
Neg logit contributions
 cand-0.016
 sweets-0.012
 candy-0.012
 bamboo-0.011
rell-0.011
Token world
Token ID995
Feature activation+9.29e-03

Pos logit contributions
 Juliet+0.008
 Doug+0.008
icker+0.008
 Donna+0.008
avi+0.008
Neg logit contributions
 cand-0.012
 sweets-0.011
rell-0.011
 candy-0.010
 bamboo-0.010
Token with
Token ID351
Feature activation+2.51e-03

Pos logit contributions
 cand+0.014
rell+0.012
 sweets+0.011
 candy+0.011
 bamboo+0.011
Neg logit contributions
 Juliet-0.018
icker-0.017
 Doug-0.017
 Donna-0.017
 broom-0.017
Token mother
Token ID2802
Feature activation+3.35e-02

Pos logit contributions
icker+0.029
 Juliet+0.028
avi+0.028
Jud+0.027
 Doug+0.026
Neg logit contributions
 cand-0.058
 sweets-0.053
 candy-0.052
 bamboo-0.050
 carn-0.048
Token holding
Token ID4769
Feature activation-1.74e-02

Pos logit contributions
 cand+0.061
rell+0.053
 sweets+0.049
 bamboo+0.047
 candy+0.047
Neg logit contributions
 Juliet-0.056
 Doug-0.055
 Donna-0.054
 broom-0.053
icker-0.052
Token a
Token ID257
Feature activation-2.89e-03

Pos logit contributions
 Juliet+0.030
icker+0.030
 Doug+0.029
avi+0.029
Jud+0.028
Neg logit contributions
 cand-0.031
 sweets-0.026
 candy-0.026
rell-0.025
 bamboo-0.025
Token freshly
Token ID29026
Feature activation-6.61e-03

Pos logit contributions
 Juliet+0.004
 Doug+0.004
icker+0.004
 Donna+0.004
avi+0.004
Neg logit contributions
 cand-0.006
rell-0.005
 sweets-0.005
 candy-0.005
 bamboo-0.005
Token-
Token ID12
Feature activation-1.99e-02

Pos logit contributions
 Juliet+0.011
icker+0.011
 Doug+0.011
 Donna+0.011
avi+0.011
Neg logit contributions
 cand-0.011
rell-0.010
 sweets-0.010
 candy-0.009
 bamboo-0.009
Tokenb
Token ID65
Feature activation-8.55e-02

Pos logit contributions
 Juliet+0.034
 Doug+0.033
icker+0.033
 Donna+0.032
avi+0.032
Neg logit contributions
 cand-0.035
 sweets-0.030
 candy-0.029
rell-0.029
 bamboo-0.028
Tokenaked
Token ID4335
Feature activation-2.23e-02

Pos logit contributions
 Juliet+0.144
Jud+0.143
 Donna+0.142
avi+0.139
icia+0.138
Neg logit contributions
hell-0.109
 cand-0.107
rell-0.102
que-0.097
 again-0.097
Token muff
Token ID27563
Feature activation-9.33e-04

Pos logit contributions
 Juliet+0.040
icker+0.040
 Doug+0.039
avi+0.039
 Donna+0.039
Neg logit contributions
 cand-0.037
 sweets-0.032
 candy-0.030
rell-0.030
 bamboo-0.029
Tokenin
Token ID259
Feature activation-3.13e-03

Pos logit contributions
 Juliet+0.001
 Doug+0.001
icker+0.001
 Donna+0.001
ox+0.001
Neg logit contributions
 cand-0.002
rell-0.002
 sweets-0.002
 candy-0.001
 bamboo-0.001
Token.
Token ID13
Feature activation-9.03e-03

Pos logit contributions
 Juliet+0.005
icker+0.005
 Doug+0.005
 Donna+0.005
avi+0.005
Neg logit contributions
 cand-0.005
rell-0.005
 sweets-0.005
 candy-0.004
 bamboo-0.004
Token
Token ID220
Feature activation-1.39e-02

Pos logit contributions
 Juliet+0.014
icker+0.014
 Doug+0.013
avi+0.013
ox+0.013
Neg logit contributions
 cand-0.017
rell-0.015
 sweets-0.015
 candy-0.014
 bamboo-0.014
Token.
Token ID13
Feature activation-1.66e-02

Pos logit contributions
 cand+0.040
rell+0.036
 sweets+0.033
 candy+0.031
reating+0.031
Neg logit contributions
 Juliet-0.037
 Doug-0.037
 broom-0.037
 Donna-0.036
icker-0.036
Token It
Token ID632
Feature activation-4.70e-04

Pos logit contributions
icker+0.029
 Juliet+0.029
ox+0.029
 broom+0.029
 Doug+0.029
Neg logit contributions
 cand-0.027
rell-0.023
 sweets-0.022
 candy-0.022
 bamboo-0.021
Token was
Token ID373
Feature activation-5.77e-03

Pos logit contributions
 Juliet+0.001
 Doug+0.001
icker+0.001
 Donna+0.001
ox+0.001
Neg logit contributions
 cand-0.001
rell-0.001
 sweets-0.001
 candy-0.001
 bamboo-0.001
Token a
Token ID257
Feature activation+1.16e-03

Pos logit contributions
 Juliet+0.009
icker+0.009
 Doug+0.009
ox+0.009
avi+0.009
Neg logit contributions
 cand-0.011
rell-0.009
 sweets-0.009
 candy-0.009
 bamboo-0.009
Token chip
Token ID11594
Feature activation+1.44e-02

Pos logit contributions
 cand+0.002
rell+0.002
 sweets+0.002
 candy+0.002
 bamboo+0.002
Neg logit contributions
 Juliet-0.002
 Doug-0.002
icker-0.002
 Donna-0.002
 broom-0.002
Tokenm
Token ID76
Feature activation-8.55e-02

Pos logit contributions
 cand+0.019
rell+0.015
 sweets+0.015
 candy+0.014
reating+0.014
Neg logit contributions
 Doug-0.030
 Juliet-0.030
icker-0.030
 broom-0.029
 Donna-0.029
Tokenunk
Token ID2954
Feature activation+4.84e-03

Pos logit contributions
 Juliet+0.091
Jud+0.087
icker+0.082
 Doug+0.080
Rachel+0.079
Neg logit contributions
 cand-0.181
rell-0.173
hell-0.166
 bamboo-0.160
 candy-0.154
Token!
Token ID0
Feature activation-6.18e-03

Pos logit contributions
 cand+0.008
rell+0.007
 sweets+0.007
 candy+0.006
 bamboo+0.006
Neg logit contributions
 Juliet-0.009
 Doug-0.008
icker-0.008
 Donna-0.008
 broom-0.008
Token The
Token ID383
Feature activation+3.17e-04

Pos logit contributions
 Juliet+0.011
icker+0.011
 Doug+0.011
ox+0.011
 broom+0.011
Neg logit contributions
 cand-0.010
rell-0.008
 sweets-0.008
 candy-0.008
 bamboo-0.008
Token chip
Token ID11594
Feature activation+1.71e-02

Pos logit contributions
 cand+0.001
rell+0.000
 sweets+0.000
 candy+0.000
 bamboo+0.000
Neg logit contributions
 Juliet-0.001
 Doug-0.001
icker-0.001
 Donna-0.001
 broom-0.001
Tokenm
Token ID76
Feature activation-7.75e-02

Pos logit contributions
 cand+0.021
rell+0.018
 sweets+0.017
reating+0.017
 carn+0.016
Neg logit contributions
 Doug-0.036
 Juliet-0.035
 Donna-0.035
icker-0.035
 broom-0.035
Token a
Token ID257
Feature activation-3.04e-02

Pos logit contributions
 Juliet+0.020
 Doug+0.020
icker+0.020
avi+0.019
 Donna+0.019
Neg logit contributions
 cand-0.023
 sweets-0.019
rell-0.019
 candy-0.019
 bamboo-0.019
Token big
Token ID1263
Feature activation+1.22e-02

Pos logit contributions
 Juliet+0.055
 Doug+0.053
 Donna+0.052
Jud+0.052
ox+0.051
Neg logit contributions
 cand-0.051
 candy-0.044
 sweets-0.042
 bamboo-0.041
 carn-0.040
Token red
Token ID2266
Feature activation+1.29e-02

Pos logit contributions
 cand+0.023
rell+0.020
 sweets+0.020
reating+0.019
 candy+0.019
Neg logit contributions
 Juliet-0.019
 Doug-0.018
icker-0.018
 human-0.018
 broom-0.018
Token bucket
Token ID19236
Feature activation+1.27e-02

Pos logit contributions
 cand+0.026
rell+0.023
 sweets+0.023
 candy+0.021
 bamboo+0.021
Neg logit contributions
 Juliet-0.018
icker-0.018
 broom-0.017
 Doug-0.017
 human-0.017
Token.
Token ID13
Feature activation-3.24e-03

Pos logit contributions
 cand+0.023
rell+0.020
 sweets+0.020
 candy+0.019
 bamboo+0.018
Neg logit contributions
 Juliet-0.020
icker-0.020
 Doug-0.019
 broom-0.019
 Donna-0.019
Token This
Token ID770
Feature activation-8.52e-02

Pos logit contributions
 Juliet+0.006
icker+0.005
 Doug+0.005
 Donna+0.005
ox+0.005
Neg logit contributions
 cand-0.006
rell-0.005
 sweets-0.005
 candy-0.005
 bamboo-0.004
Token bucket
Token ID19236
Feature activation+9.25e-03

Pos logit contributions
avi+0.182
 Juliet+0.173
 Doug+0.170
Jud+0.166
isa+0.165
Neg logit contributions
 cand-0.114
 candy-0.113
 pear-0.112
 ice-0.101
 marble-0.097
Token loved
Token ID6151
Feature activation-1.82e-02

Pos logit contributions
 cand+0.015
rell+0.013
 sweets+0.013
 candy+0.012
reating+0.012
Neg logit contributions
 Juliet-0.016
icker-0.016
 Doug-0.016
 Donna-0.016
 broom-0.016
Token to
Token ID284
Feature activation-3.31e-02

Pos logit contributions
 Juliet+0.032
icker+0.031
avi+0.030
 Doug+0.030
Jud+0.030
Neg logit contributions
 cand-0.034
 candy-0.029
 sweets-0.029
 bamboo-0.028
rell-0.027
Token gain
Token ID4461
Feature activation+1.58e-02

Pos logit contributions
 Juliet+0.066
 Doug+0.064
Jud+0.062
avi+0.062
 Donna+0.062
Neg logit contributions
 cand-0.050
 bamboo-0.042
rell-0.042
 candy-0.042
 sweets-0.042
Token things
Token ID1243
Feature activation-1.38e-03

Pos logit contributions
 cand+0.029
rell+0.026
 sweets+0.024
 carn+0.024
reating+0.023
Neg logit contributions
 Juliet-0.024
 broom-0.024
 Doug-0.023
icker-0.023
 Donna-0.023
Token the
Token ID262
Feature activation-2.55e-02

Pos logit contributions
icker+0.066
cker+0.064
ox+0.062
kins+0.062
 broom+0.062
Neg logit contributions
 cand-0.048
 sweets-0.043
 candy-0.042
 carn-0.039
reating-0.039
Token screen
Token ID3159
Feature activation-3.05e-04

Pos logit contributions
 Donna+0.035
Jud+0.035
 Juliet+0.035
icker+0.035
ox+0.035
Neg logit contributions
 cand-0.051
 sweets-0.046
 candy-0.046
rell-0.045
 carn-0.044
Token,
Token ID11
Feature activation-1.74e-02

Pos logit contributions
 Juliet+0.001
 Doug+0.000
icker+0.000
 Donna+0.000
ox+0.000
Neg logit contributions
 cand-0.001
rell-0.000
 sweets-0.000
 candy-0.000
 bamboo-0.000
Token
Token ID6184
Feature activation-3.42e-02

Pos logit contributions
icker+0.031
 Juliet+0.030
 Doug+0.030
ox+0.030
avi+0.029
Neg logit contributions
 cand-0.029
 sweets-0.024
rell-0.024
 candy-0.023
 bamboo-0.022
Token
Token ID95
Feature activation-4.52e-02

Pos logit contributions
Jud+0.053
 Juliet+0.053
 broom+0.053
 Donna+0.052
ox+0.051
Neg logit contributions
 cand-0.059
rell-0.054
 carn-0.053
 candy-0.050
 sweets-0.049
Token
Token ID26391
Feature activation-8.48e-02

Pos logit contributions
 broom+0.074
icker+0.071
 Donna+0.068
 Juliet+0.068
Jud+0.068
Neg logit contributions
rell-0.073
 cand-0.072
 carn-0.069
 course-0.064
 coaster-0.063
Token
Token ID129
Feature activation-3.20e-02

Pos logit contributions
cker+0.147
 broom+0.142
 weed+0.141
 extingu+0.138
icker+0.137
Neg logit contributions
rell-0.116
 cand-0.110
 rides-0.107
 carn-0.105
 coaster-0.105
Token
Token ID241
Feature activation-3.79e-02

Pos logit contributions
 broom+0.048
icker+0.048
 Juliet+0.046
 Doug+0.046
Jud+0.045
Neg logit contributions
 cand-0.057
rell-0.056
 carn-0.050
 sweets-0.049
 candy-0.048
TokenThat
Token ID2504
Feature activation-3.88e-02

Pos logit contributions
 broom+0.068
icker+0.068
 Doug+0.068
 Juliet+0.066
cker+0.065
Neg logit contributions
 cand-0.057
 sweets-0.049
 candy-0.049
 carn-0.048
rell-0.047
Token looks
Token ID3073
Feature activation-6.08e-03

Pos logit contributions
icker+0.088
Jud+0.082
avi+0.081
ox+0.081
 Juliet+0.081
Neg logit contributions
 cand-0.046
rell-0.037
 candy-0.037
 sweets-0.036
 carn-0.035
Token really
Token ID1107
Feature activation-5.23e-03

Pos logit contributions
 Juliet+0.011
icker+0.011
 Doug+0.011
 Donna+0.011
ox+0.010
Neg logit contributions
 cand-0.010
rell-0.008
 sweets-0.008
 candy-0.008
 bamboo-0.008
Token was
Token ID373
Feature activation-1.23e-02

Pos logit contributions
 cand+0.012
rell+0.010
 sweets+0.010
 candy+0.010
 bamboo+0.009
Neg logit contributions
 Juliet-0.013
 Doug-0.013
icker-0.013
 Donna-0.012
ox-0.012
Token a
Token ID257
Feature activation-3.29e-02

Pos logit contributions
 Juliet+0.020
 Doug+0.020
icker+0.019
avi+0.019
 Donna+0.019
Neg logit contributions
 cand-0.023
 sweets-0.019
rell-0.019
 candy-0.019
 bamboo-0.019
Token rare
Token ID4071
Feature activation-8.21e-04

Pos logit contributions
 Juliet+0.060
 Doug+0.058
 Donna+0.057
Jud+0.056
ox+0.055
Neg logit contributions
 cand-0.055
 candy-0.048
 bamboo-0.045
 sweets-0.045
 carn-0.042
Token seed
Token ID9403
Feature activation+1.58e-03

Pos logit contributions
 Juliet+0.001
 Doug+0.001
icker+0.001
 Donna+0.001
ox+0.001
Neg logit contributions
 cand-0.002
rell-0.001
 sweets-0.001
 candy-0.001
 bamboo-0.001
Token.
Token ID13
Feature activation-1.83e-03

Pos logit contributions
 cand+0.003
rell+0.002
 sweets+0.002
 candy+0.002
 bamboo+0.002
Neg logit contributions
 Juliet-0.003
icker-0.003
 Doug-0.003
 Donna-0.002
ox-0.002
Token This
Token ID770
Feature activation-8.45e-02

Pos logit contributions
 Juliet+0.003
icker+0.003
 Doug+0.003
 Donna+0.003
ox+0.003
Neg logit contributions
 cand-0.003
rell-0.003
 sweets-0.003
 candy-0.003
 bamboo-0.003
Token seed
Token ID9403
Feature activation+1.08e-02

Pos logit contributions
 Juliet+0.141
avi+0.139
 Doug+0.135
 ram+0.134
ierce+0.129
Neg logit contributions
 cand-0.151
 candy-0.134
 pear-0.129
 again-0.126
 better-0.124
Token could
Token ID714
Feature activation-3.71e-02

Pos logit contributions
 cand+0.018
rell+0.016
 sweets+0.015
 candy+0.015
reating+0.015
Neg logit contributions
 Juliet-0.019
icker-0.018
 Doug-0.018
 Donna-0.018
ox-0.018
Token grow
Token ID1663
Feature activation-1.90e-02

Pos logit contributions
 Juliet+0.067
 Doug+0.065
avi+0.063
 Karl+0.062
 Donna+0.062
Neg logit contributions
 cand-0.062
 candy-0.051
 bamboo-0.051
 sweets-0.050
rell-0.049
Token into
Token ID656
Feature activation-1.62e-02

Pos logit contributions
 Juliet+0.035
 Doug+0.035
icker+0.034
avi+0.033
 Donna+0.033
Neg logit contributions
 cand-0.031
rell-0.026
 sweets-0.026
 candy-0.025
 bamboo-0.025
Token a
Token ID257
Feature activation-1.06e-02

Pos logit contributions
 Juliet+0.031
icker+0.030
 Doug+0.030
avi+0.029
 Donna+0.029
Neg logit contributions
 cand-0.026
 sweets-0.021
 candy-0.021
 bamboo-0.020
rell-0.019
Token Then
Token ID3244
Feature activation+2.13e-02

Pos logit contributions
 cand+0.028
rell+0.023
 sweets+0.023
reating+0.022
 candy+0.022
Neg logit contributions
 Juliet-0.024
 Donna-0.023
icker-0.023
 Doug-0.023
Jud-0.022
Token,
Token ID11
Feature activation+1.32e-02

Pos logit contributions
 cand+0.033
rell+0.030
reating+0.028
 carn+0.027
 sweets+0.026
Neg logit contributions
 Juliet-0.041
 Donna-0.040
 Doug-0.039
 Judy-0.038
 Karl-0.038
Token a
Token ID257
Feature activation-4.96e-03

Pos logit contributions
 cand+0.025
rell+0.023
 sweets+0.021
 carn+0.021
 bamboo+0.020
Neg logit contributions
 Juliet-0.021
 Donna-0.020
 Doug-0.020
icker-0.019
 broom-0.019
Token small
Token ID1402
Feature activation-1.81e-02

Pos logit contributions
 Juliet+0.007
icker+0.007
 Doug+0.007
 Donna+0.006
ox+0.006
Neg logit contributions
 cand-0.010
rell-0.009
 sweets-0.009
 candy-0.009
 bamboo-0.008
Token chip
Token ID11594
Feature activation+1.00e-02

Pos logit contributions
 Juliet+0.026
icker+0.026
 Doug+0.025
ox+0.025
avi+0.025
Neg logit contributions
 cand-0.036
 candy-0.031
 sweets-0.030
rell-0.030
 bamboo-0.030
Tokenm
Token ID76
Feature activation-8.44e-02

Pos logit contributions
 cand+0.017
rell+0.015
 sweets+0.015
 candy+0.014
 carn+0.014
Neg logit contributions
 Juliet-0.017
 Doug-0.017
icker-0.016
 Donna-0.016
 broom-0.016
Tokenunk
Token ID2954
Feature activation-7.70e-03

Pos logit contributions
 Juliet+0.091
 brigade+0.081
 Doug+0.080
 pans+0.080
 Karl+0.079
Neg logit contributions
 cand-0.177
hell-0.168
rell-0.164
que-0.153
 candy-0.152
Token scrambled
Token ID34351
Feature activation-4.03e-02

Pos logit contributions
 Juliet+0.012
icker+0.012
 Doug+0.012
avi+0.012
 Donna+0.012
Neg logit contributions
 cand-0.014
rell-0.012
 sweets-0.012
 candy-0.011
 bamboo-0.011
Token down
Token ID866
Feature activation-3.35e-02

Pos logit contributions
icker+0.088
avi+0.086
ox+0.085
icia+0.083
 Juliet+0.081
Neg logit contributions
 cand-0.050
 bamboo-0.044
 candy-0.043
 again-0.043
 sweets-0.042
Token from
Token ID422
Feature activation-2.55e-02

Pos logit contributions
ox+0.079
icker+0.078
avi+0.076
icia+0.075
cker+0.074
Neg logit contributions
 cand-0.036
 bamboo-0.030
 again-0.030
 candy-0.030
 course-0.029
Token the
Token ID262
Feature activation+2.69e-02

Pos logit contributions
icker+0.055
ox+0.053
 Juliet+0.053
avi+0.053
 Doug+0.050
Neg logit contributions
 cand-0.033
 bamboo-0.029
 sweets-0.029
 candy-0.028
rell-0.027
Token scared
Token ID12008
Feature activation+4.84e-03

Pos logit contributions
 Juliet+0.086
icker+0.084
ox+0.083
 Doug+0.082
icia+0.081
Neg logit contributions
 cand-0.062
 candy-0.060
rell-0.057
 bamboo-0.057
 better-0.055
Token.
Token ID13
Feature activation-5.88e-02

Pos logit contributions
 cand+0.010
rell+0.008
 sweets+0.008
 candy+0.008
 bamboo+0.008
Neg logit contributions
 Juliet-0.007
 Doug-0.007
icker-0.007
 Donna-0.007
 broom-0.007
Token
Token ID198
Feature activation-2.89e-02

Pos logit contributions
 broom+0.143
cker+0.138
icker+0.137
kins+0.137
 extingu+0.134
Neg logit contributions
 cand-0.043
 From-0.043
rell-0.041
 -0.041
 Spark-0.035
Token
Token ID198
Feature activation-5.25e-02

Pos logit contributions
 broom+0.063
icker+0.062
cker+0.062
 stove+0.061
 Juliet+0.061
Neg logit contributions
 cand-0.030
rell-0.026
 sweets-0.023
 bamboo-0.022
 course-0.022
TokenSuddenly
Token ID38582
Feature activation-5.19e-02

Pos logit contributions
 broom+0.109
 stove+0.106
 extingu+0.106
sing+0.106
ses+0.104
Neg logit contributions
From-0.053
 course-0.051
 cand-0.050
Once-0.050
Later-0.048
Token,
Token ID11
Feature activation-8.42e-02

Pos logit contributions
cker+0.150
icker+0.149
ox+0.144
sing+0.143
 stove+0.143
Neg logit contributions
 cand-0.015
 again-0.005
 candy-0.005
 sweets-0.004
,-0.003
Token Juliet
Token ID38201
Feature activation-1.57e-02

Pos logit contributions
cker+0.138
unk+0.131
ses+0.130
sing+0.128
icker+0.126
Neg logit contributions
,-0.119
 Spark-0.117
 more-0.117
 again-0.115
 course-0.114
Token heard
Token ID2982
Feature activation-1.63e-02

Pos logit contributions
icker+0.027
 Juliet+0.026
 Doug+0.026
 Donna+0.025
 broom+0.025
Neg logit contributions
 cand-0.027
rell-0.023
 sweets-0.023
 candy-0.022
 bamboo-0.021
Token a
Token ID257
Feature activation-1.27e-02

Pos logit contributions
icker+0.026
 Juliet+0.025
 Doug+0.025
cker+0.025
 broom+0.025
Neg logit contributions
 cand-0.029
 sweets-0.025
rell-0.025
 candy-0.025
 bamboo-0.024
Token voice
Token ID3809
Feature activation-4.64e-03

Pos logit contributions
 Juliet+0.017
icker+0.016
 Doug+0.016
ox+0.016
 Donna+0.016
Neg logit contributions
 cand-0.027
 sweets-0.023
rell-0.023
 candy-0.023
 bamboo-0.023
Token.
Token ID13
Feature activation-6.82e-02

Pos logit contributions
 Juliet+0.008
icker+0.008
 Doug+0.008
 Donna+0.007
ox+0.007
Neg logit contributions
 cand-0.008
rell-0.007
 sweets-0.007
 candy-0.007
 bamboo-0.006
TokenWhen
Token ID2215
Feature activation-4.39e-02

Pos logit contributions
 broom+0.080
 stove+0.078
cker+0.078
icker+0.078
ox+0.077
Neg logit contributions
 cand-0.040
 course-0.036
From-0.035
rell-0.032
Once-0.032
Token it
Token ID340
Feature activation+2.83e-02

Pos logit contributions
cker+0.093
ox+0.093
unk+0.088
avi+0.088
icker+0.087
Neg logit contributions
 cand-0.054
 candy-0.046
 again-0.044
 course-0.044
 more-0.043
Token started
Token ID2067
Feature activation+2.26e-03

Pos logit contributions
 cand+0.058
 sweets+0.051
 candy+0.048
reating+0.048
rell+0.047
Neg logit contributions
 Juliet-0.041
 Doug-0.040
icker-0.039
 Donna-0.038
 broom-0.038
Token getting
Token ID1972
Feature activation+2.56e-02

Pos logit contributions
 cand+0.004
rell+0.004
 sweets+0.004
 candy+0.004
 bamboo+0.003
Neg logit contributions
 Juliet-0.004
 Doug-0.003
icker-0.003
 Donna-0.003
 broom-0.003
Token dark
Token ID3223
Feature activation+2.16e-03

Pos logit contributions
 cand+0.052
 sweets+0.044
rell+0.044
 carn+0.043
 bamboo+0.042
Neg logit contributions
icker-0.035
 Juliet-0.035
 Doug-0.033
 Donna-0.033
 broom-0.033
Token,
Token ID11
Feature activation-8.32e-02

Pos logit contributions
 cand+0.003
rell+0.002
 sweets+0.002
 candy+0.002
 bamboo+0.002
Neg logit contributions
 Juliet-0.005
 Doug-0.004
icker-0.004
 Donna-0.004
 broom-0.004
Token Mild
Token ID29087
Feature activation-4.06e-02

Pos logit contributions
cker+0.163
ox+0.162
icker+0.158
unk+0.157
zzy+0.149
Neg logit contributions
 more-0.100
 again-0.091
 better-0.088
 course-0.085
 cand-0.084
Token and
Token ID290
Feature activation-4.55e-02

Pos logit contributions
icker+0.077
 Juliet+0.074
Jud+0.071
 Donna+0.071
 Doug+0.071
Neg logit contributions
 cand-0.062
rell-0.053
 sweets-0.049
 candy-0.048
 carn-0.045
Token her
Token ID607
Feature activation-4.56e-02

Pos logit contributions
avi+0.083
icker+0.081
cker+0.079
ox+0.078
ower+0.078
Neg logit contributions
 cand-0.070
 candy-0.059
 sweets-0.057
 Spark-0.055
reating-0.055
Token brother
Token ID3956
Feature activation+2.13e-02

Pos logit contributions
Jud+0.072
 Juliet+0.064
avi+0.064
 Judy+0.063
cker+0.062
Neg logit contributions
 cand-0.090
 candy-0.078
 sweets-0.074
rell-0.072
 carn-0.068
Token returned
Token ID4504
Feature activation-1.47e-02

Pos logit contributions
 cand+0.036
rell+0.030
 sweets+0.030
 candy+0.029
 bamboo+0.029
Neg logit contributions
 Juliet-0.038
 Doug-0.037
 Donna-0.036
icker-0.036
 broom-0.036
Token forgot
Token ID16453
Feature activation+2.64e-02

Pos logit contributions
 cand+0.046
rell+0.040
reating+0.039
 bamboo+0.038
 sweets+0.037
Neg logit contributions
 Juliet-0.040
 Donna-0.038
 Doug-0.038
 Judy-0.037
Jud-0.036
Token all
Token ID477
Feature activation+3.26e-02

Pos logit contributions
 cand+0.038
rell+0.033
 carn+0.029
 bamboo+0.028
 sweets+0.027
Neg logit contributions
 Juliet-0.053
 Doug-0.050
 Donna-0.050
 broom-0.050
 Judy-0.050
Token about
Token ID546
Feature activation-3.82e-03

Pos logit contributions
 cand+0.050
rell+0.042
 sweets+0.037
 carn+0.036
 coaster+0.035
Neg logit contributions
 Juliet-0.061
 Judy-0.060
 Donna-0.059
 human-0.058
 broom-0.058
Token the
Token ID262
Feature activation-8.06e-03

Pos logit contributions
 Juliet+0.007
icker+0.007
 Doug+0.007
 Donna+0.007
ox+0.007
Neg logit contributions
 cand-0.006
 sweets-0.005
rell-0.005
 candy-0.005
 bamboo-0.005
Token marsh
Token ID22397
Feature activation-1.13e-02

Pos logit contributions
 Juliet+0.014
icker+0.014
 Doug+0.014
avi+0.014
 Donna+0.014
Neg logit contributions
 cand-0.014
 sweets-0.012
rell-0.011
 candy-0.011
 bamboo-0.011
Tokenm
Token ID76
Feature activation-8.28e-02

Pos logit contributions
 Juliet+0.025
 Doug+0.025
icker+0.024
 Donna+0.024
ox+0.024
Neg logit contributions
 cand-0.014
 sweets-0.011
rell-0.011
 candy-0.010
 bamboo-0.010
Tokenallows
Token ID47205
Feature activation+1.12e-02

Pos logit contributions
 Juliet+0.113
 Doug+0.103
Jud+0.102
Doug+0.101
 Donna+0.100
Neg logit contributions
rell-0.163
 cand-0.162
hell-0.148
 sweets-0.144
 bamboo-0.143
Token.
Token ID13
Feature activation+3.52e-02

Pos logit contributions
 cand+0.019
rell+0.016
 sweets+0.016
 candy+0.015
 bamboo+0.015
Neg logit contributions
 Juliet-0.019
icker-0.018
 Doug-0.018
 Donna-0.018
 broom-0.018
Token<|endoftext|>
Token ID50256
Feature activation+9.94e-03

Pos logit contributions
 cand+0.062
 sweets+0.052
reating+0.051
rell+0.050
 carn+0.048
Neg logit contributions
 Juliet-0.060
 Donna-0.058
 Doug-0.057
 Judy-0.056
icker-0.056
TokenOnce
Token ID7454
Feature activation-5.76e-03

Pos logit contributions
 cand+0.017
 sweets+0.014
rell+0.014
 candy+0.013
 bamboo+0.013
Neg logit contributions
 Juliet-0.018
 Doug-0.017
icker-0.017
 Donna-0.017
Jud-0.016
Token upon
Token ID2402
Feature activation-4.68e-03

Pos logit contributions
 Juliet+0.008
 Doug+0.007
icker+0.007
 Donna+0.007
avi+0.007
Neg logit contributions
 cand-0.012
rell-0.011
 sweets-0.010
 candy-0.010
 bamboo-0.010
Token the
Token ID262
Feature activation+2.72e-02

Pos logit contributions
 Doug+0.056
cker+0.056
ox+0.055
icker+0.055
 Juliet+0.055
Neg logit contributions
 cand-0.038
 sweets-0.032
 candy-0.030
rell-0.028
 again-0.027
Token park
Token ID3952
Feature activation-7.53e-03

Pos logit contributions
 cand+0.049
rell+0.045
 sweets+0.040
reating+0.038
hell+0.037
Neg logit contributions
 broom-0.044
 human-0.043
 Juliet-0.042
icker-0.042
 tractor-0.041
Token.
Token ID13
Feature activation-2.55e-02

Pos logit contributions
 Juliet+0.013
 Doug+0.013
icker+0.013
 Donna+0.013
avi+0.013
Neg logit contributions
 cand-0.013
rell-0.011
 sweets-0.011
 candy-0.010
 bamboo-0.010
Token She
Token ID1375
Feature activation-6.23e-04

Pos logit contributions
 broom+0.048
icker+0.048
cker+0.047
 Doug+0.047
avi+0.046
Neg logit contributions
 cand-0.037
rell-0.033
 sweets-0.030
 candy-0.029
 carn-0.028
Token felt
Token ID2936
Feature activation+2.72e-02

Pos logit contributions
 Juliet+0.001
 Doug+0.001
icker+0.001
 Donna+0.001
ox+0.001
Neg logit contributions
 cand-0.001
rell-0.001
 sweets-0.001
 candy-0.001
 bamboo-0.001
Token much
Token ID881
Feature activation+5.46e-02

Pos logit contributions
 cand+0.048
rell+0.041
 sweets+0.037
reating+0.036
 bamboo+0.036
Neg logit contributions
 Juliet-0.048
icker-0.045
 Donna-0.045
 Doug-0.043
 Judy-0.043
Token better
Token ID1365
Feature activation-1.25e-02

Pos logit contributions
 cand+0.079
rell+0.074
reating+0.072
 carn+0.067
 bamboo+0.065
Neg logit contributions
 broom-0.096
icker-0.095
 Juliet-0.090
 Donna-0.088
 human-0.087
Token now
Token ID783
Feature activation+1.60e-02

Pos logit contributions
 Juliet+0.025
 Doug+0.025
icker+0.025
 Donna+0.024
Jud+0.024
Neg logit contributions
 cand-0.018
 sweets-0.014
 candy-0.014
rell-0.014
 carn-0.013
Token that
Token ID326
Feature activation-7.84e-04

Pos logit contributions
 cand+0.029
rell+0.025
 bamboo+0.024
 sweets+0.024
 candy+0.022
Neg logit contributions
 Juliet-0.027
 Donna-0.026
 Doug-0.025
icker-0.025
 broom-0.025
Token she
Token ID673
Feature activation-1.12e-02

Pos logit contributions
 Juliet+0.001
 Doug+0.001
icker+0.001
 Donna+0.001
ox+0.001
Neg logit contributions
 cand-0.001
rell-0.001
 sweets-0.001
 candy-0.001
 bamboo-0.001
Token had
Token ID550
Feature activation+8.93e-03

Pos logit contributions
 Juliet+0.020
icker+0.020
 Doug+0.019
 Donna+0.019
Jud+0.019
Neg logit contributions
 cand-0.019
 sweets-0.016
rell-0.016
 candy-0.015
 carn-0.015
Token sw
Token ID1509
Feature activation-1.52e-02

Pos logit contributions
 Juliet+0.025
icker+0.024
 Doug+0.024
 broom+0.023
 Donna+0.023
Neg logit contributions
 cand-0.016
rell-0.012
 sweets-0.012
 candy-0.011
 bamboo-0.011
Tokenam
Token ID321
Feature activation-1.92e-03

Pos logit contributions
 Juliet+0.032
 Doug+0.031
 Donna+0.031
 broom+0.030
icker+0.030
Neg logit contributions
 cand-0.021
rell-0.017
 sweets-0.016
 bamboo-0.016
 candy-0.015
Token together
Token ID1978
Feature activation-5.72e-03

Pos logit contributions
 Juliet+0.003
 Doug+0.003
icker+0.003
 Donna+0.003
avi+0.003
Neg logit contributions
 cand-0.003
rell-0.003
 sweets-0.003
 candy-0.003
 bamboo-0.003
Token every
Token ID790
Feature activation+7.48e-03

Pos logit contributions
 Juliet+0.011
 Doug+0.010
icker+0.010
 Donna+0.010
avi+0.010
Neg logit contributions
 cand-0.009
rell-0.008
 sweets-0.007
 candy-0.007
 bamboo-0.007
Token day
Token ID1110
Feature activation-2.34e-02

Pos logit contributions
 cand+0.012
rell+0.010
 sweets+0.009
 candy+0.009
 bamboo+0.009
Neg logit contributions
 Juliet-0.014
 Doug-0.014
icker-0.014
 Donna-0.014
 human-0.014
Token.
Token ID13
Feature activation+5.42e-02

Pos logit contributions
 Juliet+0.045
 Doug+0.043
icker+0.043
 Donna+0.043
ox+0.042
Neg logit contributions
 cand-0.036
rell-0.029
 sweets-0.029
 candy-0.028
 bamboo-0.027
Token<|endoftext|>
Token ID50256
Feature activation+1.90e-02

Pos logit contributions
 cand+0.114
 sweets+0.104
reating+0.102
rell+0.098
 Seek+0.094
Neg logit contributions
icker-0.065
 Donna-0.059
 human-0.058
 Juliet-0.057
 Doug-0.057
TokenOnce
Token ID7454
Feature activation-5.04e-03

Pos logit contributions
 cand+0.035
 sweets+0.029
rell+0.029
 candy+0.027
reating+0.027
Neg logit contributions
 Juliet-0.032
icker-0.031
 Doug-0.031
Jud-0.029
 Donna-0.029
Token upon
Token ID2402
Feature activation-1.55e-02

Pos logit contributions
 Juliet+0.007
 Doug+0.007
icker+0.007
 Donna+0.006
avi+0.006
Neg logit contributions
 cand-0.010
rell-0.009
 sweets-0.009
 candy-0.009
 bamboo-0.009
Token a
Token ID257
Feature activation-1.69e-02

Pos logit contributions
 Juliet+0.026
 Doug+0.025
 Donna+0.025
icker+0.024
avi+0.024
Neg logit contributions
 cand-0.028
 sweets-0.024
 candy-0.024
rell-0.024
 bamboo-0.023
Token time
Token ID640
Feature activation+1.27e-02

Pos logit contributions
 Juliet+0.031
 Doug+0.030
 Donna+0.029
icker+0.029
 broom+0.029
Neg logit contributions
 cand-0.028
rell-0.023
 sweets-0.023
 candy-0.022
 bamboo-0.022
Token and
Token ID290
Feature activation+2.35e-02

Pos logit contributions
 cand+0.018
rell+0.016
 sweets+0.015
 bamboo+0.014
 candy+0.014
Neg logit contributions
 Juliet-0.018
 Doug-0.018
 broom-0.017
icker-0.017
 Donna-0.017
Token the
Token ID262
Feature activation+1.19e-02

Pos logit contributions
 cand+0.042
rell+0.040
 sweets+0.036
 bamboo+0.035
hell+0.034
Neg logit contributions
 Juliet-0.038
 Doug-0.037
 human-0.035
 broom-0.035
 Donna-0.035
Token kids
Token ID3988
Feature activation+3.18e-02

Pos logit contributions
 cand+0.023
rell+0.021
 sweets+0.019
 bamboo+0.019
reating+0.018
Neg logit contributions
 Juliet-0.018
 broom-0.017
 Doug-0.017
icker-0.017
 human-0.017
Token never
Token ID1239
Feature activation+3.59e-02

Pos logit contributions
 cand+0.058
rell+0.051
 sweets+0.049
 bamboo+0.048
reating+0.047
Neg logit contributions
 Juliet-0.050
icker-0.049
 broom-0.048
 Doug-0.047
avi-0.047
Token saw
Token ID2497
Feature activation-6.77e-03

Pos logit contributions
 cand+0.075
rell+0.067
 sweets+0.067
 bamboo+0.065
reating+0.063
Neg logit contributions
 Juliet-0.045
 Doug-0.044
 human-0.043
 broom-0.043
Jud-0.043
Token him
Token ID683
Feature activation+5.33e-02

Pos logit contributions
 Juliet+0.013
icker+0.013
 Doug+0.012
 Donna+0.012
ox+0.012
Neg logit contributions
 cand-0.011
 sweets-0.009
rell-0.009
 candy-0.009
 bamboo-0.008
Token again
Token ID757
Feature activation+1.33e-02

Pos logit contributions
 cand+0.068
rell+0.061
 sweets+0.050
 bamboo+0.049
rob+0.046
Neg logit contributions
icker-0.107
 broom-0.104
 human-0.103
 Juliet-0.102
 Doug-0.101
Token.
Token ID13
Feature activation+4.68e-03

Pos logit contributions
 cand+0.027
rell+0.024
 sweets+0.023
 bamboo+0.022
 candy+0.022
Neg logit contributions
 Juliet-0.019
icker-0.018
 Doug-0.018
 human-0.018
avi-0.017
Token<|endoftext|>
Token ID50256
Feature activation+4.26e-03

Pos logit contributions
 cand+0.008
 sweets+0.006
rell+0.006
 candy+0.006
 bamboo+0.006
Neg logit contributions
 Juliet-0.009
 Doug-0.008
icker-0.008
 Donna-0.008
avi-0.008
TokenOnce
Token ID7454
Feature activation-2.33e-02

Pos logit contributions
 cand+0.007
rell+0.006
 sweets+0.006
 candy+0.005
 bamboo+0.005
Neg logit contributions
 Juliet-0.008
 Doug-0.008
icker-0.008
 Donna-0.007
avi-0.007
Token upon
Token ID2402
Feature activation-2.57e-02

Pos logit contributions
 Juliet+0.037
avi+0.036
 Doug+0.036
ox+0.035
 Donna+0.035
Neg logit contributions
 cand-0.042
rell-0.036
 sweets-0.035
 candy-0.035
 bamboo-0.034
Token big
Token ID1263
Feature activation+2.10e-02

Pos logit contributions
 cand+0.001
rell+0.001
 sweets+0.001
 candy+0.001
 bamboo+0.001
Neg logit contributions
 Juliet-0.001
icker-0.001
 Doug-0.001
 Donna-0.001
 broom-0.001
Token hug
Token ID16225
Feature activation+4.33e-03

Pos logit contributions
 cand+0.033
rell+0.028
 sweets+0.027
reating+0.025
 carn+0.025
Neg logit contributions
 broom-0.040
 Juliet-0.038
icker-0.038
 Doug-0.038
 human-0.037
Token.
Token ID13
Feature activation+1.79e-02

Pos logit contributions
 cand+0.008
rell+0.007
 sweets+0.007
 candy+0.007
 bamboo+0.007
Neg logit contributions
 Juliet-0.007
 Doug-0.007
icker-0.006
 Donna-0.006
 broom-0.006
Token Tim
Token ID5045
Feature activation+2.21e-02

Pos logit contributions
 cand+0.031
 sweets+0.025
reating+0.025
rell+0.025
 bamboo+0.024
Neg logit contributions
 Doug-0.031
 Juliet-0.031
 Donna-0.031
icker-0.030
 Judy-0.030
Tokenmy
Token ID1820
Feature activation+2.62e-02

Pos logit contributions
 cand+0.034
 sweets+0.028
rell+0.027
 bamboo+0.026
 carn+0.026
Neg logit contributions
ox-0.043
 Juliet-0.042
 Doug-0.042
 human-0.041
 broom-0.041
Token felt
Token ID2936
Feature activation+5.26e-02

Pos logit contributions
 cand+0.048
rell+0.044
reating+0.043
 sweets+0.042
 bamboo+0.041
Neg logit contributions
ox-0.040
 broom-0.039
 Juliet-0.039
 Doug-0.038
 human-0.038
Token much
Token ID881
Feature activation+5.65e-02

Pos logit contributions
 cand+0.093
rell+0.087
reating+0.080
 carn+0.079
 coaster+0.077
Neg logit contributions
icker-0.077
 broom-0.073
 Donna-0.072
 human-0.072
 curious-0.072
Token better
Token ID1365
Feature activation+6.62e-03

Pos logit contributions
 cand+0.072
rell+0.067
 carn+0.066
reating+0.065
 sweets+0.060
Neg logit contributions
 broom-0.112
icker-0.109
 tool-0.102
 human-0.102
 Donna-0.101
Token.
Token ID13
Feature activation+1.68e-02

Pos logit contributions
 cand+0.012
rell+0.010
 sweets+0.010
 bamboo+0.009
 candy+0.009
Neg logit contributions
 Juliet-0.011
icker-0.011
 Doug-0.011
 Donna-0.011
ox-0.011
Token
Token ID198
Feature activation+1.92e-02

Pos logit contributions
 cand+0.029
 sweets+0.025
rell+0.024
reating+0.024
 bamboo+0.023
Neg logit contributions
 Juliet-0.029
 Doug-0.029
icker-0.028
 Donna-0.028
 Judy-0.027
Token
Token ID198
Feature activation+1.44e-02

Pos logit contributions
 cand+0.035
rell+0.029
 sweets+0.029
 candy+0.027
 carn+0.027
Neg logit contributions
 Juliet-0.032
icker-0.032
 Doug-0.032
Jud-0.031
 Donna-0.031
Token better
Token ID1365
Feature activation+2.49e-03

Pos logit contributions
 cand+0.070
rell+0.066
reating+0.060
 carn+0.058
 coaster+0.058
Neg logit contributions
icker-0.053
 Juliet-0.052
 Donna-0.050
 Doug-0.050
 Judy-0.050
Token.
Token ID13
Feature activation+1.98e-02

Pos logit contributions
 cand+0.005
rell+0.004
 sweets+0.004
 candy+0.004
 bamboo+0.004
Neg logit contributions
 Juliet-0.004
icker-0.004
 Doug-0.004
 Donna-0.004
avi-0.004
Token He
Token ID679
Feature activation+2.70e-02

Pos logit contributions
 cand+0.036
rell+0.031
 sweets+0.030
reating+0.030
 bamboo+0.029
Neg logit contributions
 Juliet-0.032
 Doug-0.031
 Donna-0.030
icker-0.030
 human-0.029
Token looked
Token ID3114
Feature activation+2.49e-02

Pos logit contributions
 cand+0.047
rell+0.045
reating+0.042
 sweets+0.041
 bamboo+0.038
Neg logit contributions
 Doug-0.043
 Juliet-0.043
 human-0.041
cker-0.041
avi-0.041
Token at
Token ID379
Feature activation+1.54e-02

Pos logit contributions
 cand+0.051
rell+0.047
reating+0.043
 sweets+0.042
 carn+0.042
Neg logit contributions
 Juliet-0.034
icker-0.033
 Doug-0.032
 Donna-0.032
 broom-0.032
Token Lily
Token ID20037
Feature activation+5.67e-02

Pos logit contributions
 cand+0.027
rell+0.023
 sweets+0.023
 carn+0.022
 candy+0.021
Neg logit contributions
 Doug-0.026
 Juliet-0.026
 Donna-0.025
 human-0.024
icker-0.024
Token and
Token ID290
Feature activation+2.74e-02

Pos logit contributions
 cand+0.114
rell+0.110
 carn+0.103
reating+0.103
 sweets+0.100
Neg logit contributions
 human-0.069
 broom-0.068
ox-0.068
icker-0.067
 Doug-0.066
Token said
Token ID531
Feature activation+3.76e-02

Pos logit contributions
rell+0.052
 cand+0.051
reating+0.045
 sweets+0.044
 bamboo+0.044
Neg logit contributions
 Juliet-0.041
 Doug-0.041
 Donna-0.039
 Judy-0.039
 human-0.039
Token,
Token ID11
Feature activation+4.22e-03

Pos logit contributions
 cand+0.060
rell+0.058
 carn+0.055
reating+0.052
 sweets+0.049
Neg logit contributions
 Doug-0.063
 Juliet-0.063
icker-0.061
 Judy-0.060
 Donna-0.059
Token "
Token ID366
Feature activation+4.15e-03

Pos logit contributions
 cand+0.009
rell+0.008
 sweets+0.008
 candy+0.008
 bamboo+0.007
Neg logit contributions
 Juliet-0.006
 Doug-0.005
icker-0.005
 Donna-0.005
avi-0.005
TokenThank
Token ID10449
Feature activation+1.44e-03

Pos logit contributions
 cand+0.007
rell+0.006
 sweets+0.006
 candy+0.005
 bamboo+0.005
Neg logit contributions
 Juliet-0.008
 Doug-0.007
icker-0.007
 Donna-0.007
Jud-0.007
Token in
Token ID287
Feature activation-7.93e-03

Pos logit contributions
 cand+0.004
rell+0.004
 sweets+0.004
 candy+0.004
 bamboo+0.003
Neg logit contributions
 Juliet-0.005
icker-0.005
 Doug-0.005
 Donna-0.005
 broom-0.005
Token his
Token ID465
Feature activation-1.62e-02

Pos logit contributions
 Juliet+0.016
icker+0.016
 Donna+0.015
 Doug+0.015
avi+0.015
Neg logit contributions
 cand-0.012
rell-0.009
 sweets-0.009
 candy-0.009
 bamboo-0.009
Token bedroom
Token ID14043
Feature activation-1.20e-02

Pos logit contributions
 Juliet+0.025
Jud+0.024
 Donna+0.024
icker+0.024
avi+0.024
Neg logit contributions
 cand-0.031
 candy-0.027
 sweets-0.027
 bamboo-0.026
rell-0.025
Token before
Token ID878
Feature activation-2.90e-03

Pos logit contributions
 Juliet+0.022
 Doug+0.021
 Donna+0.021
icker+0.021
Jud+0.021
Neg logit contributions
 cand-0.020
 sweets-0.016
rell-0.016
 candy-0.016
 bamboo-0.015
Token bed
Token ID3996
Feature activation+1.02e-02

Pos logit contributions
 Juliet+0.005
 Doug+0.005
icker+0.005
 Donna+0.005
ox+0.005
Neg logit contributions
 cand-0.005
rell-0.004
 sweets-0.004
 candy-0.004
 bamboo-0.004
Tokentime
Token ID2435
Feature activation+1.87e-02

Pos logit contributions
 cand+0.018
rell+0.016
 sweets+0.015
 bamboo+0.015
 candy+0.014
Neg logit contributions
 Juliet-0.017
icker-0.017
 Doug-0.016
 broom-0.016
 Donna-0.016
Token.
Token ID13
Feature activation+1.08e-02

Pos logit contributions
 cand+0.035
rell+0.031
 sweets+0.030
 bamboo+0.029
 course+0.028
Neg logit contributions
 Juliet-0.029
 Doug-0.028
 Donna-0.027
 broom-0.027
 human-0.027
Token He
Token ID679
Feature activation+1.61e-02

Pos logit contributions
 cand+0.019
rell+0.016
 sweets+0.016
reating+0.015
 bamboo+0.015
Neg logit contributions
 Doug-0.018
 Juliet-0.018
icker-0.018
 Donna-0.018
 broom-0.017
Token held
Token ID2714
Feature activation-9.60e-03

Pos logit contributions
 cand+0.031
rell+0.028
 sweets+0.027
reating+0.026
 bamboo+0.026
Neg logit contributions
 Juliet-0.024
 Doug-0.023
 broom-0.023
ox-0.023
 human-0.022
Token the
Token ID262
Feature activation+9.07e-03

Pos logit contributions
 Juliet+0.019
icker+0.019
Jud+0.018
avi+0.018
 Donna+0.018
Neg logit contributions
 cand-0.014
 sweets-0.012
 candy-0.012
rell-0.011
 bamboo-0.011
Token rock
Token ID3881
Feature activation-1.68e-05

Pos logit contributions
 cand+0.017
rell+0.015
 sweets+0.014
 bamboo+0.013
reating+0.013
Neg logit contributions
 Juliet-0.015
 broom-0.014
 Doug-0.014
icker-0.014
 human-0.014
Token said
Token ID531
Feature activation-3.50e-03

Pos logit contributions
 Juliet+0.027
icker+0.027
 Doug+0.026
 Donna+0.026
Jud+0.025
Neg logit contributions
 cand-0.020
rell-0.017
 sweets-0.016
 candy-0.016
 bamboo-0.015
Token.
Token ID13
Feature activation+1.59e-02

Pos logit contributions
 Juliet+0.007
icker+0.007
 Doug+0.007
 Donna+0.007
ox+0.007
Neg logit contributions
 cand-0.005
rell-0.004
 sweets-0.004
 candy-0.004
 bamboo-0.004
Token
Token ID198
Feature activation+1.69e-02

Pos logit contributions
 cand+0.028
 sweets+0.024
rell+0.024
 candy+0.022
 bamboo+0.022
Neg logit contributions
 Juliet-0.027
 Doug-0.026
 Donna-0.026
icker-0.025
 Karl-0.025
Token
Token ID198
Feature activation+2.42e-02

Pos logit contributions
 cand+0.032
 sweets+0.026
rell+0.026
 candy+0.025
reating+0.024
Neg logit contributions
 Juliet-0.028
 Doug-0.028
Jud-0.027
 Donna-0.027
icker-0.027
TokenThe
Token ID464
Feature activation+2.08e-02

Pos logit contributions
 cand+0.050
rell+0.043
 sweets+0.043
 candy+0.040
 bamboo+0.039
Neg logit contributions
 Juliet-0.034
Jud-0.033
 Doug-0.033
avi-0.033
 Donna-0.033
Token angel
Token ID18304
Feature activation+4.78e-03

Pos logit contributions
 cand+0.045
rell+0.042
reating+0.039
 sweets+0.038
hell+0.036
Neg logit contributions
 human-0.027
 Doug-0.026
 Juliet-0.025
 tractor-0.024
 Donna-0.024
Token waved
Token ID26834
Feature activation-1.12e-02

Pos logit contributions
 cand+0.008
rell+0.007
 sweets+0.006
 candy+0.006
 bamboo+0.006
Neg logit contributions
 Juliet-0.009
 Doug-0.009
icker-0.008
 Donna-0.008
 broom-0.008
Token her
Token ID607
Feature activation-3.04e-02

Pos logit contributions
icker+0.024
 Juliet+0.024
 Doug+0.024
Jud+0.023
 Donna+0.023
Neg logit contributions
 cand-0.014
 sweets-0.011
rell-0.011
 candy-0.011
 bamboo-0.010
Token hands
Token ID2832
Feature activation-1.30e-02

Pos logit contributions
 Juliet+0.047
Jud+0.046
icker+0.046
arge+0.044
 Donna+0.043
Neg logit contributions
 cand-0.057
 sweets-0.050
 candy-0.049
rell-0.048
 bamboo-0.047
Token and
Token ID290
Feature activation+2.08e-02

Pos logit contributions
 Juliet+0.025
icker+0.024
 Doug+0.024
avi+0.023
ox+0.023
Neg logit contributions
 cand-0.020
rell-0.017
 sweets-0.017
 candy-0.016
 bamboo-0.016
Token the
Token ID262
Feature activation+1.27e-02

Pos logit contributions
 cand+0.038
rell+0.033
 sweets+0.032
reating+0.031
 bamboo+0.031
Neg logit contributions
 Juliet-0.035
 Doug-0.034
 Donna-0.033
 Judy-0.032
Jud-0.032
Token on
Token ID319
Feature activation-1.91e-02

Pos logit contributions
 Juliet+0.014
icker+0.014
 Doug+0.014
 Donna+0.014
Jud+0.014
Neg logit contributions
 cand-0.013
 sweets-0.011
rell-0.011
 candy-0.011
 bamboo-0.010
Token him
Token ID683
Feature activation+5.33e-03

Pos logit contributions
icker+0.034
 Juliet+0.034
 Doug+0.033
Jud+0.033
ox+0.033
Neg logit contributions
 cand-0.031
 sweets-0.027
 candy-0.026
rell-0.026
 carn-0.024
Token.
Token ID13
Feature activation+5.55e-02

Pos logit contributions
 cand+0.009
rell+0.008
 sweets+0.008
 candy+0.008
 bamboo+0.008
Neg logit contributions
 Juliet-0.009
 Doug-0.009
icker-0.009
 Donna-0.008
ox-0.008
Token
Token ID198
Feature activation+4.60e-02

Pos logit contributions
 cand+0.121
 sweets+0.110
reating+0.108
 bamboo+0.107
 mango+0.103
Neg logit contributions
 Mother-0.060
 Karl-0.058
 Doug-0.055
 Donna-0.055
icker-0.055
Token
Token ID198
Feature activation+5.27e-02

Pos logit contributions
 cand+0.087
 sweets+0.072
rell+0.071
 candy+0.066
reating+0.063
Neg logit contributions
icker-0.077
 Juliet-0.072
 Doug-0.072
 human-0.070
ox-0.070
TokenFrom
Token ID4863
Feature activation+2.47e-02

Pos logit contributions
 cand+0.103
rell+0.091
 sweets+0.089
 bamboo+0.088
 mango+0.084
Neg logit contributions
icker-0.070
icia-0.068
 tractor-0.068
Doug-0.066
 human-0.066
Token that
Token ID326
Feature activation+2.32e-02

Pos logit contributions
 cand+0.039
rell+0.034
 sweets+0.031
hell+0.028
 candy+0.028
Neg logit contributions
 Juliet-0.049
 Doug-0.047
 Donna-0.047
 human-0.046
icker-0.046
Token day
Token ID1110
Feature activation+3.96e-02

Pos logit contributions
 cand+0.045
 sweets+0.037
rell+0.037
 bamboo+0.037
 candy+0.035
Neg logit contributions
 Juliet-0.037
 human-0.037
 Doug-0.037
 Donna-0.035
icker-0.035
Token on
Token ID319
Feature activation+2.70e-02

Pos logit contributions
 cand+0.078
 sweets+0.067
 bamboo+0.065
 carn+0.063
rell+0.063
Neg logit contributions
 Doug-0.059
icker-0.059
 Juliet-0.059
 broom-0.057
 Donna-0.056
Token,
Token ID11
Feature activation+5.19e-02

Pos logit contributions
 cand+0.041
reating+0.034
 sweets+0.034
rell+0.034
 bamboo+0.033
Neg logit contributions
 Doug-0.050
 Donna-0.049
 Juliet-0.049
 Karl-0.048
 broom-0.048
Token Red
Token ID2297
Feature activation+3.08e-03

Pos logit contributions
 cand+0.071
 bamboo+0.065
rell+0.062
ogging+0.062
reating+0.061
Neg logit contributions
 human-0.086
 Donna-0.085
 Doug-0.085
 Karl-0.085
 Mother-0.085
Token'm
Token ID1101
Feature activation-2.48e-02

Pos logit contributions
 Juliet+0.085
icker+0.084
 Doug+0.083
avi+0.080
Jud+0.080
Neg logit contributions
 cand-0.066
 candy-0.057
 carn-0.053
 sweets-0.053
 course-0.050
Token studying
Token ID11065
Feature activation+4.59e-04

Pos logit contributions
icker+0.044
ox+0.044
 Juliet+0.043
avi+0.043
Jud+0.043
Neg logit contributions
 cand-0.040
 sweets-0.034
 candy-0.034
rell-0.033
 bamboo-0.032
Token!"
Token ID2474
Feature activation+1.33e-02

Pos logit contributions
 cand+0.001
rell+0.001
 sweets+0.001
 candy+0.001
 bamboo+0.001
Neg logit contributions
 Juliet-0.001
 Doug-0.001
icker-0.001
 Donna-0.001
ox-0.001
Token The
Token ID383
Feature activation-3.77e-02

Pos logit contributions
 cand+0.024
rell+0.021
 sweets+0.021
reating+0.020
 bamboo+0.020
Neg logit contributions
 Doug-0.021
 Juliet-0.021
icker-0.021
 Donna-0.020
 human-0.020
Token little
Token ID1310
Feature activation-3.08e-02

Pos logit contributions
Jud+0.074
 Juliet+0.073
 Judy+0.071
 Donna+0.070
 Doug+0.068
Neg logit contributions
 cand-0.061
 candy-0.054
 sweets-0.049
 carn-0.048
rell-0.046
Token boy
Token ID2933
Feature activation+1.81e-02

Pos logit contributions
 Juliet+0.064
Jud+0.063
 Donna+0.060
 Doug+0.059
avi+0.059
Neg logit contributions
 cand-0.049
 candy-0.041
 sweets-0.037
rell-0.037
 carn-0.035
Token was
Token ID373
Feature activation+2.67e-03

Pos logit contributions
 cand+0.034
rell+0.030
 sweets+0.029
reating+0.028
 bamboo+0.028
Neg logit contributions
 Juliet-0.028
 Doug-0.028
icker-0.027
ox-0.027
avi-0.027
Token so
Token ID523
Feature activation-1.43e-02

Pos logit contributions
 cand+0.004
rell+0.004
 sweets+0.003
 candy+0.003
 bamboo+0.003
Neg logit contributions
 Juliet-0.005
 Doug-0.005
icker-0.005
 Donna-0.005
 broom-0.005
Token amazed
Token ID24562
Feature activation-1.45e-02

Pos logit contributions
 Juliet+0.026
ox+0.026
 Doug+0.025
 broom+0.025
 Donna+0.025
Neg logit contributions
 cand-0.023
 sweets-0.019
rell-0.019
 candy-0.018
 carn-0.017
Token.
Token ID13
Feature activation+2.19e-03

Pos logit contributions
 Juliet+0.030
icker+0.030
 broom+0.029
ox+0.029
 Doug+0.029
Neg logit contributions
 cand-0.020
 sweets-0.016
 candy-0.016
rell-0.016
 bamboo-0.015
Token He
Token ID679
Feature activation+1.08e-02

Pos logit contributions
 cand+0.004
rell+0.003
 sweets+0.003
 candy+0.003
 bamboo+0.003
Neg logit contributions
 Juliet-0.004
 Doug-0.004
icker-0.004
 Donna-0.004
avi-0.004
Token to
Token ID284
Feature activation-1.32e-02

Pos logit contributions
 Juliet+0.015
 Doug+0.015
icker+0.015
 Donna+0.015
ox+0.015
Neg logit contributions
 cand-0.018
rell-0.015
 sweets-0.015
 candy-0.015
 bamboo-0.014
Token her
Token ID607
Feature activation+1.07e-02

Pos logit contributions
icker+0.028
 Juliet+0.027
ox+0.027
 broom+0.027
avi+0.027
Neg logit contributions
 cand-0.017
 sweets-0.014
rell-0.014
 candy-0.014
 bamboo-0.013
Token and
Token ID290
Feature activation-1.13e-02

Pos logit contributions
 cand+0.019
rell+0.017
 sweets+0.015
 bamboo+0.015
 carn+0.015
Neg logit contributions
 Juliet-0.018
icker-0.018
 Doug-0.018
 broom-0.018
 human-0.018
Token played
Token ID2826
Feature activation+2.47e-04

Pos logit contributions
 Juliet+0.020
icker+0.020
 Doug+0.020
ox+0.019
 broom+0.019
Neg logit contributions
 cand-0.019
 sweets-0.016
rell-0.015
 candy-0.015
 bamboo-0.014
Token baseball
Token ID9283
Feature activation+1.81e-02

Pos logit contributions
 cand+0.000
rell+0.000
 sweets+0.000
 candy+0.000
 bamboo+0.000
Neg logit contributions
 Juliet-0.000
 Doug-0.000
icker-0.000
 Donna-0.000
 broom-0.000
Token safely
Token ID11512
Feature activation+2.54e-02

Pos logit contributions
 cand+0.028
rell+0.023
 sweets+0.022
 candy+0.021
reating+0.021
Neg logit contributions
 Juliet-0.033
icker-0.033
 Doug-0.033
 broom-0.033
 Donna-0.032
Token.
Token ID13
Feature activation-7.82e-03

Pos logit contributions
 cand+0.050
 sweets+0.042
rell+0.041
 candy+0.039
 bamboo+0.039
Neg logit contributions
icker-0.037
 Juliet-0.037
 broom-0.036
 Doug-0.036
 human-0.035
Token<|endoftext|>
Token ID50256
Feature activation+1.72e-02

Pos logit contributions
 Juliet+0.015
icker+0.015
 Doug+0.015
 broom+0.015
ox+0.015
Neg logit contributions
 cand-0.012
rell-0.010
 sweets-0.009
 candy-0.009
 bamboo-0.009
TokenSteve
Token ID19206
Feature activation-3.83e-03

Pos logit contributions
 cand+0.033
 sweets+0.027
rell+0.027
 candy+0.026
reating+0.025
Neg logit contributions
 Juliet-0.028
 Doug-0.027
icker-0.026
 Donna-0.026
Jud-0.025
Token was
Token ID373
Feature activation+3.74e-04

Pos logit contributions
 Juliet+0.007
icker+0.006
 Doug+0.006
 Donna+0.006
 broom+0.006
Neg logit contributions
 cand-0.007
rell-0.006
 sweets-0.006
 candy-0.005
 bamboo-0.005
Token a
Token ID257
Feature activation-3.90e-02

Pos logit contributions
 cand+0.001
rell+0.001
 sweets+0.001
 candy+0.001
 bamboo+0.001
Neg logit contributions
 Juliet-0.001
 Doug-0.001
icker-0.001
 Donna-0.001
 broom-0.001
Token
Token ID198
Feature activation+5.99e-03

Pos logit contributions
 cand+0.002
rell+0.002
 sweets+0.002
 candy+0.002
 bamboo+0.002
Neg logit contributions
 Juliet-0.003
 Doug-0.003
icker-0.003
 Donna-0.003
avi-0.003
Token"
Token ID1
Feature activation+1.96e-02

Pos logit contributions
 cand+0.011
rell+0.010
 sweets+0.010
 candy+0.009
 bamboo+0.009
Neg logit contributions
 Juliet-0.010
 Doug-0.009
icker-0.009
Jud-0.009
 Donna-0.009
TokenHello
Token ID15496
Feature activation+2.54e-02

Pos logit contributions
 cand+0.033
rell+0.029
 sweets+0.028
 candy+0.026
 bamboo+0.026
Neg logit contributions
 Juliet-0.033
 Doug-0.033
Jud-0.033
avi-0.032
Doug-0.032
Token,
Token ID11
Feature activation+3.01e-02

Pos logit contributions
 cand+0.036
rell+0.033
 sweets+0.029
reating+0.027
 bamboo+0.027
Neg logit contributions
 Juliet-0.051
 Doug-0.049
avi-0.049
 human-0.048
 Karl-0.048
Token kids
Token ID3988
Feature activation+2.86e-02

Pos logit contributions
 cand+0.052
rell+0.048
 sweets+0.043
 bamboo+0.040
 candy+0.039
Neg logit contributions
 Juliet-0.051
 Doug-0.049
 human-0.049
avi-0.047
 Karl-0.047
Token!"
Token ID2474
Feature activation-3.10e-03

Pos logit contributions
 cand+0.052
rell+0.045
 sweets+0.044
 candy+0.041
 bamboo+0.041
Neg logit contributions
 Juliet-0.045
 Doug-0.044
avi-0.044
ox-0.043
icker-0.043
Token the
Token ID262
Feature activation-9.59e-04

Pos logit contributions
 Juliet+0.006
icker+0.006
 Doug+0.006
 Donna+0.006
ox+0.006
Neg logit contributions
 cand-0.005
rell-0.004
 sweets-0.004
 candy-0.004
 bamboo-0.004
Token clown
Token ID25573
Feature activation+2.78e-02

Pos logit contributions
 Juliet+0.001
 Doug+0.001
icker+0.001
 Donna+0.001
ox+0.001
Neg logit contributions
 cand-0.002
rell-0.002
 sweets-0.002
 candy-0.002
 bamboo-0.002
Token said
Token ID531
Feature activation-1.30e-02

Pos logit contributions
 cand+0.052
rell+0.047
 sweets+0.047
reating+0.045
 bamboo+0.044
Neg logit contributions
 Juliet-0.044
 Doug-0.043
avi-0.041
icker-0.041
 human-0.040
Token.
Token ID13
Feature activation-1.51e-02

Pos logit contributions
 Juliet+0.024
 Doug+0.023
icker+0.023
 Donna+0.023
ox+0.023
Neg logit contributions
 cand-0.021
 sweets-0.017
rell-0.017
 candy-0.017
 bamboo-0.016
Token "
Token ID366
Feature activation+6.23e-03

Pos logit contributions
icker+0.025
 Juliet+0.025
ox+0.024
 Donna+0.024
icia+0.024
Neg logit contributions
 cand-0.026
rell-0.023
 candy-0.022
 sweets-0.022
 bamboo-0.022
Token wide
Token ID3094
Feature activation+2.80e-02

Pos logit contributions
 cand+0.014
rell+0.012
 sweets+0.012
 carn+0.011
 candy+0.011
Neg logit contributions
 Juliet-0.010
icker-0.010
 Doug-0.010
 broom-0.010
 Donna-0.010
Token and
Token ID290
Feature activation-1.14e-02

Pos logit contributions
 cand+0.052
rell+0.047
 sweets+0.044
 carn+0.043
 bamboo+0.043
Neg logit contributions
 Juliet-0.041
 broom-0.041
 Doug-0.039
icker-0.039
 stove-0.039
Token he
Token ID339
Feature activation-2.53e-02

Pos logit contributions
icker+0.019
 Juliet+0.019
avi+0.019
ox+0.019
 Doug+0.019
Neg logit contributions
 cand-0.020
 sweets-0.017
 candy-0.017
rell-0.016
 bamboo-0.016
Token smiled
Token ID13541
Feature activation-2.65e-02

Pos logit contributions
 Juliet+0.046
icker+0.045
 Donna+0.045
 Doug+0.044
avi+0.043
Neg logit contributions
 cand-0.042
 sweets-0.034
 candy-0.033
 bamboo-0.032
rell-0.032
Token.
Token ID13
Feature activation-1.33e-02

Pos logit contributions
 Juliet+0.054
 Doug+0.053
ox+0.053
Jud+0.053
avi+0.053
Neg logit contributions
 cand-0.036
 candy-0.031
 sweets-0.030
 again-0.029
rell-0.028
Token He
Token ID679
Feature activation-1.90e-02

Pos logit contributions
 Juliet+0.027
icker+0.027
avi+0.026
ox+0.026
 Donna+0.026
Neg logit contributions
 cand-0.018
rell-0.015
 sweets-0.015
 candy-0.014
 bamboo-0.014
Token saw
Token ID2497
Feature activation+9.03e-03

Pos logit contributions
icker+0.034
 Juliet+0.033
 Doug+0.032
 Donna+0.032
ox+0.031
Neg logit contributions
 cand-0.033
 sweets-0.027
 candy-0.026
rell-0.025
 carn-0.025
Token lots
Token ID6041
Feature activation+5.21e-02

Pos logit contributions
 cand+0.016
rell+0.014
 sweets+0.013
 bamboo+0.012
 candy+0.012
Neg logit contributions
 Juliet-0.016
 Doug-0.016
icker-0.015
 broom-0.015
 Donna-0.015
Token of
Token ID286
Feature activation+2.62e-02

Pos logit contributions
rell+0.085
 cand+0.082
 carn+0.073
ieved+0.068
shadow+0.068
Neg logit contributions
 human-0.080
 broom-0.078
 stove-0.076
 Doug-0.075
 pots-0.074
Token exciting
Token ID7895
Feature activation+1.79e-02

Pos logit contributions
 cand+0.047
rell+0.046
 carn+0.040
reating+0.040
 bamboo+0.039
Neg logit contributions
 broom-0.038
 Juliet-0.037
 human-0.037
icker-0.037
 stove-0.036
Token things
Token ID1243
Feature activation+1.17e-02

Pos logit contributions
 cand+0.033
rell+0.030
 sweets+0.028
 carn+0.027
 bamboo+0.027
Neg logit contributions
 Juliet-0.026
 broom-0.026
 Doug-0.025
icker-0.025
 human-0.025
Token
Token ID198
Feature activation+1.22e-02

Pos logit contributions
 Juliet+0.047
 Doug+0.046
cker+0.046
 broom+0.046
icker+0.046
Neg logit contributions
 cand-0.029
rell-0.025
 sweets-0.022
 candy-0.021
 bamboo-0.021
TokenThen
Token ID6423
Feature activation-4.26e-03

Pos logit contributions
 cand+0.021
 sweets+0.017
rell+0.017
 candy+0.017
 carn+0.016
Neg logit contributions
 Juliet-0.022
 Doug-0.022
icker-0.021
Jud-0.021
 Donna-0.021
Token they
Token ID484
Feature activation+7.20e-03

Pos logit contributions
 Juliet+0.009
icker+0.008
 Doug+0.008
 Donna+0.008
ox+0.008
Neg logit contributions
 cand-0.006
 sweets-0.005
rell-0.005
 candy-0.005
 bamboo-0.005
Token watched
Token ID7342
Feature activation-1.84e-02

Pos logit contributions
 cand+0.013
rell+0.011
 sweets+0.010
 candy+0.010
 bamboo+0.010
Neg logit contributions
 Juliet-0.013
 Doug-0.012
icker-0.012
 Donna-0.012
Jud-0.012
Token the
Token ID262
Feature activation+2.87e-02

Pos logit contributions
 Juliet+0.037
ox+0.036
icker+0.036
Jud+0.036
 Doug+0.036
Neg logit contributions
 cand-0.026
 sweets-0.022
 candy-0.021
rell-0.020
 bamboo-0.020
Token sun
Token ID4252
Feature activation-3.10e-03

Pos logit contributions
 cand+0.056
rell+0.052
 sweets+0.046
reating+0.044
 bamboo+0.044
Neg logit contributions
 human-0.041
icker-0.041
 Juliet-0.040
 broom-0.040
 Doug-0.040
Token set
Token ID900
Feature activation-2.48e-02

Pos logit contributions
 Juliet+0.006
 Doug+0.006
icker+0.005
 Donna+0.005
ox+0.005
Neg logit contributions
 cand-0.005
rell-0.004
 sweets-0.004
 candy-0.004
 bamboo-0.004
Token over
Token ID625
Feature activation-3.98e-02

Pos logit contributions
 Juliet+0.052
 Doug+0.052
ox+0.052
icker+0.051
avi+0.051
Neg logit contributions
 cand-0.032
rell-0.027
 sweets-0.026
 candy-0.025
 bamboo-0.023
Token the
Token ID262
Feature activation+3.41e-02

Pos logit contributions
ox+0.094
icker+0.089
 ram+0.089
cker+0.089
avi+0.088
Neg logit contributions
 cand-0.042
 again-0.037
 sweets-0.035
 candy-0.034
 course-0.033
Token dark
Token ID3223
Feature activation+1.56e-03

Pos logit contributions
 cand+0.071
rell+0.063
 sweets+0.058
reating+0.058
 bamboo+0.056
Neg logit contributions
 human-0.045
 broom-0.045
 stove-0.044
icker-0.044
 Juliet-0.044
Token hill
Token ID12788
Feature activation-1.45e-02

Pos logit contributions
 cand+0.003
rell+0.002
 sweets+0.002
 candy+0.002
 bamboo+0.002
Neg logit contributions
 Juliet-0.003
 Doug-0.003
icker-0.003
 Donna-0.003
 broom-0.003
Token kids
Token ID3988
Feature activation+2.99e-03

Pos logit contributions
 cand+0.041
rell+0.035
 sweets+0.034
 bamboo+0.033
 candy+0.032
Neg logit contributions
 Juliet-0.038
 human-0.037
 broom-0.037
ox-0.037
avi-0.036
Token first
Token ID717
Feature activation+1.28e-03

Pos logit contributions
 cand+0.005
rell+0.004
 sweets+0.004
 candy+0.004
 bamboo+0.004
Neg logit contributions
 Juliet-0.005
 Doug-0.005
icker-0.005
 Donna-0.005
 broom-0.005
Token".
Token ID1911
Feature activation-2.44e-02

Pos logit contributions
 cand+0.002
rell+0.002
 sweets+0.002
 candy+0.002
 bamboo+0.002
Neg logit contributions
 Juliet-0.002
 Doug-0.002
icker-0.002
 Donna-0.002
ox-0.002
Token
Token ID198
Feature activation-1.02e-02

Pos logit contributions
ox+0.049
 broom+0.048
cker+0.048
 Juliet+0.048
avi+0.048
Neg logit contributions
 cand-0.033
rell-0.027
 sweets-0.027
 candy-0.026
 carn-0.024
TokenJack
Token ID14295
Feature activation-1.30e-02

Pos logit contributions
 Juliet+0.021
 Doug+0.020
icker+0.020
 broom+0.020
ox+0.020
Neg logit contributions
 cand-0.014
rell-0.011
 sweets-0.011
 candy-0.011
 bamboo-0.010
Token nodded
Token ID14464
Feature activation-2.81e-02

Pos logit contributions
 Juliet+0.024
icker+0.024
 Doug+0.023
 Donna+0.023
 broom+0.023
Neg logit contributions
 cand-0.021
rell-0.017
 sweets-0.017
 candy-0.016
 bamboo-0.015
Token,
Token ID11
Feature activation+5.58e-03

Pos logit contributions
 Juliet+0.059
icker+0.059
ox+0.058
 Doug+0.058
icia+0.058
Neg logit contributions
 cand-0.036
 sweets-0.030
 candy-0.028
 again-0.027
rell-0.027
Token disappointed
Token ID11679
Feature activation+1.21e-02

Pos logit contributions
 cand+0.009
rell+0.008
 sweets+0.008
 candy+0.007
 bamboo+0.007
Neg logit contributions
 Juliet-0.010
 Doug-0.010
icker-0.010
 Donna-0.010
 broom-0.009
Token.
Token ID13
Feature activation-1.78e-02

Pos logit contributions
 cand+0.022
rell+0.019
 sweets+0.018
 bamboo+0.018
 carn+0.018
Neg logit contributions
 Juliet-0.020
 Doug-0.019
icker-0.019
 Donna-0.019
avi-0.018
Token
Token ID198
Feature activation-8.78e-03

Pos logit contributions
 Juliet+0.037
ox+0.037
 broom+0.037
icker+0.037
avi+0.036
Neg logit contributions
 cand-0.023
rell-0.019
 sweets-0.019
 candy-0.018
 carn-0.016
Token
Token ID198
Feature activation-1.98e-02

Pos logit contributions
 Juliet+0.018
icker+0.017
 Doug+0.017
 broom+0.017
ox+0.017
Neg logit contributions
 cand-0.012
rell-0.010
 sweets-0.010
 candy-0.009
 bamboo-0.009
Token beard
Token ID21213
Feature activation+9.50e-03

Pos logit contributions
icker+0.033
 Juliet+0.033
 Doug+0.033
 Donna+0.032
icia+0.032
Neg logit contributions
 cand-0.044
 candy-0.038
 sweets-0.038
rell-0.036
 carn-0.035
Token and
Token ID290
Feature activation-3.87e-02

Pos logit contributions
 cand+0.018
rell+0.015
 sweets+0.015
 candy+0.014
 bamboo+0.014
Neg logit contributions
 Juliet-0.015
 Doug-0.014
icker-0.014
avi-0.014
ox-0.014
Token a
Token ID257
Feature activation-2.46e-02

Pos logit contributions
icker+0.075
icia+0.070
 Juliet+0.068
Jud+0.067
 Donna+0.067
Neg logit contributions
 cand-0.063
 candy-0.056
 sweets-0.053
 bamboo-0.049
rell-0.049
Token robe
Token ID33192
Feature activation+1.56e-02

Pos logit contributions
 Juliet+0.036
icker+0.035
 Doug+0.035
 Donna+0.034
icia+0.034
Neg logit contributions
 cand-0.050
 candy-0.043
 sweets-0.043
rell-0.041
 bamboo-0.040
Token.
Token ID13
Feature activation-1.78e-02

Pos logit contributions
 cand+0.031
rell+0.027
 sweets+0.027
 candy+0.025
 bamboo+0.025
Neg logit contributions
 Juliet-0.022
icker-0.021
 Doug-0.021
avi-0.021
 broom-0.021
Token He
Token ID679
Feature activation-2.05e-03

Pos logit contributions
icker+0.039
 Juliet+0.038
icia+0.038
 broom+0.037
 Doug+0.037
Neg logit contributions
 cand-0.022
rell-0.018
 candy-0.018
 sweets-0.017
 bamboo-0.017
Token looks
Token ID3073
Feature activation+8.28e-03

Pos logit contributions
 Juliet+0.004
icker+0.003
 Doug+0.003
 Donna+0.003
ox+0.003
Neg logit contributions
 cand-0.004
rell-0.003
 sweets-0.003
 candy-0.003
 bamboo-0.003
Token angry
Token ID7954
Feature activation+7.02e-03

Pos logit contributions
 cand+0.016
rell+0.014
 sweets+0.014
 candy+0.013
 bamboo+0.013
Neg logit contributions
 Juliet-0.012
 Doug-0.012
icker-0.012
 Donna-0.011
 broom-0.011
Token.
Token ID13
Feature activation-2.60e-02

Pos logit contributions
 cand+0.014
rell+0.012
 sweets+0.012
 candy+0.011
 bamboo+0.011
Neg logit contributions
 Juliet-0.011
 Doug-0.010
icker-0.010
 Donna-0.010
 broom-0.010
Token
Token ID198
Feature activation-4.83e-03

Pos logit contributions
icker+0.061
icia+0.060
 Juliet+0.059
 broom+0.059
cker+0.057
Neg logit contributions
 cand-0.028
 candy-0.022
rell-0.022
 bamboo-0.021
 sweets-0.020
Token
Token ID198
Feature activation-9.90e-03

Pos logit contributions
 Juliet+0.010
icker+0.009
 Doug+0.009
 Donna+0.009
 broom+0.009
Neg logit contributions
 cand-0.007
rell-0.006
 sweets-0.006
 candy-0.006
 bamboo-0.005
Token help
Token ID1037
Feature activation-3.09e-02

Pos logit contributions
 Juliet+0.029
 Doug+0.028
icker+0.028
ox+0.027
 Donna+0.027
Neg logit contributions
 cand-0.024
 sweets-0.020
rell-0.020
 candy-0.020
 bamboo-0.019
Token her
Token ID607
Feature activation-2.70e-02

Pos logit contributions
 Juliet+0.057
 Doug+0.056
icker+0.055
avi+0.055
cker+0.055
Neg logit contributions
 cand-0.049
 sweets-0.042
 candy-0.041
rell-0.038
reating-0.037
Token make
Token ID787
Feature activation-4.09e-02

Pos logit contributions
 Juliet+0.048
 Doug+0.047
Jud+0.046
avi+0.046
 Donna+0.046
Neg logit contributions
 cand-0.046
 sweets-0.039
 candy-0.038
rell-0.035
 again-0.035
Token the
Token ID262
Feature activation+5.36e-03

Pos logit contributions
cker+0.084
avi+0.082
 Doug+0.081
 Juliet+0.080
icker+0.080
Neg logit contributions
 cand-0.060
 sweets-0.050
 candy-0.049
rell-0.044
 again-0.043
Token cob
Token ID22843
Feature activation-4.83e-02

Pos logit contributions
 cand+0.012
rell+0.010
 sweets+0.010
 candy+0.010
 bamboo+0.010
Neg logit contributions
 Juliet-0.007
icker-0.007
 Doug-0.007
 broom-0.007
 Donna-0.006
Tokenwe
Token ID732
Feature activation-6.20e-02

Pos logit contributions
 Doug+0.073
 Juliet+0.073
 Donna+0.070
 Karl+0.070
avi+0.069
Neg logit contributions
 cand-0.091
 bamboo-0.078
 again-0.078
rell-0.076
 sweets-0.074
Tokenbs
Token ID1443
Feature activation-3.03e-02

Pos logit contributions
 Doug+0.086
 Juliet+0.083
avi+0.081
Jud+0.080
 Donna+0.080
Neg logit contributions
 cand-0.123
 sweets-0.113
rell-0.112
 candy-0.109
 course-0.104
Token.
Token ID13
Feature activation-1.73e-04

Pos logit contributions
 Juliet+0.058
 Doug+0.057
icker+0.056
avi+0.056
Jud+0.055
Neg logit contributions
 cand-0.047
rell-0.039
 sweets-0.039
 candy-0.037
 bamboo-0.036
Token They
Token ID1119
Feature activation-1.77e-02

Pos logit contributions
 Juliet+0.000
 Doug+0.000
icker+0.000
 Donna+0.000
ox+0.000
Neg logit contributions
 cand-0.000
rell-0.000
 sweets-0.000
 candy-0.000
 bamboo-0.000
Token loved
Token ID6151
Feature activation-3.81e-02

Pos logit contributions
 Juliet+0.035
icker+0.034
 Doug+0.034
avi+0.034
ox+0.034
Neg logit contributions
 cand-0.026
 sweets-0.021
rell-0.021
 candy-0.020
 bamboo-0.019
Token playing
Token ID2712
Feature activation-3.22e-02

Pos logit contributions
icker+0.080
cker+0.078
avi+0.078
 Juliet+0.077
ox+0.077
Neg logit contributions
 cand-0.055
 sweets-0.047
 candy-0.046
 bamboo-0.040
 sharing-0.039
Token beautiful
Token ID4950
Feature activation+2.83e-02

Pos logit contributions
 cand+0.033
rell+0.030
 sweets+0.029
reating+0.027
 bamboo+0.027
Neg logit contributions
 Juliet-0.020
 Doug-0.019
icker-0.019
 human-0.019
 broom-0.019
Token bracelet
Token ID42893
Feature activation+1.30e-02

Pos logit contributions
 cand+0.059
rell+0.054
 sweets+0.050
reating+0.048
 candy+0.046
Neg logit contributions
 Juliet-0.039
 human-0.037
 Donna-0.037
 broom-0.036
 Doug-0.036
Token on
Token ID319
Feature activation-1.29e-02

Pos logit contributions
 cand+0.023
rell+0.020
 sweets+0.020
 candy+0.019
 bamboo+0.018
Neg logit contributions
 Juliet-0.021
 broom-0.021
 Doug-0.021
icker-0.021
 Donna-0.020
Token the
Token ID262
Feature activation+1.89e-02

Pos logit contributions
icker+0.025
 Juliet+0.025
ox+0.024
 Doug+0.024
avi+0.024
Neg logit contributions
 cand-0.020
 sweets-0.016
rell-0.016
 candy-0.016
 bamboo-0.016
Token ground
Token ID2323
Feature activation+3.54e-03

Pos logit contributions
 cand+0.033
rell+0.028
 sweets+0.028
 candy+0.026
 carn+0.026
Neg logit contributions
 Juliet-0.032
 human-0.031
 Donna-0.031
 Doug-0.030
 broom-0.030
Token.
Token ID13
Feature activation-5.65e-02

Pos logit contributions
 cand+0.007
rell+0.006
 sweets+0.006
 candy+0.005
 bamboo+0.005
Neg logit contributions
 Juliet-0.006
icker-0.005
 Doug-0.005
 Donna-0.005
 broom-0.005
Token It
Token ID632
Feature activation+1.99e-02

Pos logit contributions
cker+0.128
 extingu+0.122
icker+0.121
 broom+0.121
 tractor+0.118
Neg logit contributions
 From-0.058
 cand-0.054
 -0.053
rell-0.048
 sweets-0.048
Token was
Token ID373
Feature activation+2.63e-02

Pos logit contributions
 cand+0.037
rell+0.032
reating+0.032
 sweets+0.032
 candy+0.030
Neg logit contributions
 Juliet-0.031
 Doug-0.030
 Donna-0.030
Jud-0.029
 broom-0.029
Token so
Token ID523
Feature activation+1.58e-02

Pos logit contributions
 cand+0.046
rell+0.041
 sweets+0.037
reating+0.036
 carn+0.035
Neg logit contributions
 Juliet-0.045
 Donna-0.043
 Doug-0.042
 broom-0.042
 human-0.041
Token shiny
Token ID22441
Feature activation+4.04e-03

Pos logit contributions
 cand+0.035
rell+0.032
 sweets+0.030
reating+0.030
 carn+0.029
Neg logit contributions
 Juliet-0.020
icker-0.019
 Donna-0.019
Jud-0.018
 Doug-0.018
Token and
Token ID290
Feature activation-1.05e-02

Pos logit contributions
 cand+0.007
rell+0.006
 sweets+0.005
 candy+0.005
 bamboo+0.005
Neg logit contributions
 Juliet-0.007
 Doug-0.007
icker-0.007
 Donna-0.007
 broom-0.007
Token smiled
Token ID13541
Feature activation-2.09e-02

Pos logit contributions
 cand+0.005
rell+0.005
 sweets+0.004
 candy+0.004
 bamboo+0.004
Neg logit contributions
 Juliet-0.006
 Doug-0.006
icker-0.006
 Donna-0.006
 broom-0.006
Token and
Token ID290
Feature activation-9.53e-03

Pos logit contributions
 Doug+0.045
Jud+0.044
icker+0.044
 Juliet+0.044
ox+0.044
Neg logit contributions
 cand-0.028
 candy-0.022
 sweets-0.022
 again-0.021
rell-0.020
Token said
Token ID531
Feature activation+6.42e-04

Pos logit contributions
 Juliet+0.019
icker+0.019
 Doug+0.019
ox+0.019
avi+0.018
Neg logit contributions
 cand-0.014
 sweets-0.011
rell-0.011
 candy-0.011
 bamboo-0.010
Token
Token ID6184
Feature activation-1.70e-02

Pos logit contributions
 cand+0.001
rell+0.001
 sweets+0.001
 candy+0.001
 bamboo+0.001
Neg logit contributions
 Juliet-0.001
 Doug-0.001
icker-0.001
 Donna-0.001
 broom-0.001
Token
Token ID95
Feature activation-2.32e-02

Pos logit contributions
 Juliet+0.028
 Doug+0.028
icker+0.026
 Donna+0.026
 broom+0.026
Neg logit contributions
 cand-0.031
 sweets-0.026
rell-0.026
 candy-0.025
 bamboo-0.025
Token
Token ID26391
Feature activation-7.07e-02

Pos logit contributions
 Doug+0.039
 Juliet+0.038
icker+0.037
 broom+0.037
cker+0.036
Neg logit contributions
 cand-0.040
rell-0.035
 sweets-0.034
 carn-0.033
 candy-0.033
Token
Token ID129
Feature activation-1.60e-02

Pos logit contributions
cker+0.143
 Doug+0.129
icker+0.126
 extingu+0.123
 ram+0.123
Neg logit contributions
 cand-0.101
 candy-0.081
 sweets-0.081
rell-0.079
 again-0.076
Token
Token ID241
Feature activation-4.32e-02

Pos logit contributions
 Juliet+0.025
 Doug+0.024
icker+0.024
 broom+0.024
ox+0.023
Neg logit contributions
 cand-0.030
rell-0.027
 sweets-0.026
 bamboo-0.025
 candy-0.025
Tokenyes
Token ID8505
Feature activation+4.95e-04

Pos logit contributions
cker+0.087
 Doug+0.085
icker+0.084
 broom+0.083
 tractor+0.083
Neg logit contributions
 cand-0.059
 candy-0.052
 sweets-0.051
 bamboo-0.047
 carn-0.047
Token,
Token ID11
Feature activation-1.15e-02

Pos logit contributions
 cand+0.001
rell+0.000
 sweets+0.000
 candy+0.000
 bamboo+0.000
Neg logit contributions
 Juliet-0.001
 Doug-0.001
icker-0.001
 Donna-0.001
 broom-0.001
Tokenâ
Token ID22940
Feature activation-4.37e-04

Pos logit contributions
icker+0.021
 Juliet+0.021
 Doug+0.021
ox+0.021
avi+0.021
Neg logit contributions
 cand-0.018
 sweets-0.015
 candy-0.015
rell-0.014
 bamboo-0.014
Token a
Token ID257
Feature activation+1.12e-02

Pos logit contributions
 Juliet+0.013
icker+0.013
 Doug+0.012
avi+0.012
 Donna+0.012
Neg logit contributions
 cand-0.012
 sweets-0.010
rell-0.010
 candy-0.010
 bamboo-0.010
Token special
Token ID2041
Feature activation+1.55e-02

Pos logit contributions
 cand+0.022
rell+0.019
 sweets+0.018
 bamboo+0.017
 candy+0.017
Neg logit contributions
 Juliet-0.017
 broom-0.016
 Doug-0.016
icker-0.016
 Donna-0.016
Token home
Token ID1363
Feature activation-9.83e-03

Pos logit contributions
 cand+0.031
rell+0.028
 sweets+0.026
 bamboo+0.025
reating+0.025
Neg logit contributions
 Juliet-0.022
 broom-0.021
 Doug-0.021
icker-0.021
 Donna-0.021
Token
Token ID6184
Feature activation-5.64e-03

Pos logit contributions
 Juliet+0.018
icker+0.017
 Doug+0.017
avi+0.017
 Donna+0.017
Neg logit contributions
 cand-0.016
 sweets-0.014
rell-0.014
 candy-0.013
 bamboo-0.013
Token
Token ID95
Feature activation-2.16e-02

Pos logit contributions
 Juliet+0.009
 Doug+0.009
icker+0.009
 Donna+0.009
ox+0.008
Neg logit contributions
 cand-0.010
rell-0.009
 sweets-0.009
 candy-0.009
 bamboo-0.008
Token
Token ID26391
Feature activation-5.88e-02

Pos logit contributions
 Doug+0.036
icker+0.036
 broom+0.036
 Juliet+0.035
ox+0.034
Neg logit contributions
 cand-0.036
rell-0.033
 carn-0.031
 sweets-0.030
 candy-0.029
Token
Token ID447
Feature activation+1.53e-02

Pos logit contributions
cker+0.125
icker+0.122
 broom+0.122
 stove+0.121
 extingu+0.119
Neg logit contributions
 cand-0.061
rell-0.058
 carn-0.053
Once-0.048
 sweets-0.048
Token
Token ID250
Feature activation-3.11e-03

Pos logit contributions
 cand+0.032
 sweets+0.027
rell+0.027
reating+0.027
 bamboo+0.026
Neg logit contributions
icker-0.021
 Juliet-0.021
 Doug-0.021
 Donna-0.020
avi-0.020
Token a
Token ID257
Feature activation-1.69e-03

Pos logit contributions
 Juliet+0.005
 Doug+0.005
icker+0.005
 Donna+0.005
 broom+0.004
Neg logit contributions
 cand-0.006
rell-0.005
 sweets-0.005
 candy-0.005
 bamboo-0.005
Token hut
Token ID40812
Feature activation-1.99e-02

Pos logit contributions
 Juliet+0.003
 Doug+0.003
icker+0.003
 Donna+0.003
ox+0.002
Neg logit contributions
 cand-0.003
rell-0.003
 sweets-0.003
 candy-0.003
 bamboo-0.003
Token.
Token ID13
Feature activation-3.77e-03

Pos logit contributions
 Juliet+0.040
icker+0.040
 Doug+0.039
ox+0.039
avi+0.039
Neg logit contributions
 cand-0.029
 sweets-0.023
rell-0.023
 candy-0.022
 bamboo-0.021
Token to
Token ID284
Feature activation-8.47e-03

Pos logit contributions
 Juliet+0.004
icker+0.004
 Doug+0.004
 Donna+0.004
ox+0.003
Neg logit contributions
 cand-0.003
rell-0.003
 sweets-0.003
 candy-0.003
 bamboo-0.003
Token her
Token ID607
Feature activation+1.25e-02

Pos logit contributions
 Juliet+0.016
icker+0.016
 Doug+0.016
 Donna+0.016
 broom+0.016
Neg logit contributions
 cand-0.013
rell-0.010
 sweets-0.010
 candy-0.010
 bamboo-0.010
Token!"
Token ID2474
Feature activation-3.72e-02

Pos logit contributions
 cand+0.021
rell+0.018
 sweets+0.018
 candy+0.017
 bamboo+0.017
Neg logit contributions
 Juliet-0.022
 Doug-0.021
icker-0.021
 broom-0.021
ox-0.021
Token Mia
Token ID32189
Feature activation+5.08e-03

Pos logit contributions
icker+0.068
cker+0.067
ox+0.067
icia+0.067
ower+0.063
Neg logit contributions
 cand-0.056
 candy-0.049
 bamboo-0.048
 sweets-0.045
 course-0.044
Token says
Token ID1139
Feature activation-2.36e-02

Pos logit contributions
 cand+0.009
 sweets+0.008
rell+0.008
 candy+0.007
 bamboo+0.007
Neg logit contributions
 Juliet-0.009
 Doug-0.008
icker-0.008
 Donna-0.008
avi-0.008
Token.
Token ID13
Feature activation-5.67e-02

Pos logit contributions
 Juliet+0.047
 Doug+0.046
 Donna+0.045
Jud+0.044
icia+0.044
Neg logit contributions
 cand-0.035
rell-0.028
 sweets-0.028
 candy-0.027
 again-0.027
Token She
Token ID1375
Feature activation+7.71e-03

Pos logit contributions
cker+0.153
icia+0.150
icker+0.150
kins+0.145
ox+0.143
Neg logit contributions
 cand-0.033
 From-0.027
 candy-0.026
 -0.026
 again-0.024
Token hugs
Token ID40657
Feature activation-4.59e-02

Pos logit contributions
 cand+0.013
rell+0.011
 sweets+0.011
 candy+0.010
 bamboo+0.010
Neg logit contributions
 Juliet-0.013
 Doug-0.013
 broom-0.013
icker-0.013
 Donna-0.013
Token Anna
Token ID11735
Feature activation+2.36e-02

Pos logit contributions
icker+0.090
cker+0.088
icia+0.084
ox+0.084
 dunno+0.083
Neg logit contributions
 cand-0.063
 bamboo-0.059
 again-0.056
 course-0.055
 candy-0.054
Token and
Token ID290
Feature activation-1.03e-02

Pos logit contributions
 cand+0.049
rell+0.044
 carn+0.043
 sweets+0.042
reating+0.041
Neg logit contributions
 Juliet-0.031
 human-0.031
 broom-0.031
ox-0.030
 Doug-0.030
Token checks
Token ID8794
Feature activation-4.33e-02

Pos logit contributions
icker+0.021
 Juliet+0.021
 Doug+0.020
 Donna+0.020
Jud+0.020
Neg logit contributions
 cand-0.015
 sweets-0.012
rell-0.012
 candy-0.012
 bamboo-0.011